Search Results for author:
Found 186 papers, 105 papers with code
MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification
For the meta learner, it requires a good generalization ability so as to quickly adapt to new tasks.
Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases
Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints.
Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution
In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution.
CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
We propose two variants for our CLIPure approach: CLIPure-Diff which models the likelihood of images' latent vectors with the DiffusionPrior module in DaLLE-2 (modeling the generation process of CLIP's latent vectors), and CLIPure-Cos which models the likelihood with the cosine similarity between the embeddings of an image and ``a photo of a.''.
Estimating Commonsense Plausibility through Semantic Shifts
Commonsense plausibility estimation is critical for evaluating language models (LMs), yet existing generative approaches--reliant on likelihoods or verbalized judgments--struggle with fine-grained discrimination.
TrustRAG: An Information Assistant with Retrieval Augmented Generation
To address this gap, we introduce TrustRAG, a novel framework that enhances \ac{RAG} from three perspectives: indexing, retrieval, and generation.
Revisiting Robust RAG: Do We Still Need Complex Robust Training in the Era of Powerful LLMs?
Our findings suggest that RAG systems can benefit from simpler architectures and training strategies as models become more powerful, enabling more scalable applications with minimal complexity.
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
The conditional distribution alignment task focuses on aligning text embeddings with positive samples embeddings by leveraging the conditional distribution of embeddings while simultaneously reducing the likelihood of generating negative samples from text embeddings, thereby achieving embedding alignment and uniformity.
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
Large language models (LLMs) exhibit impressive performance across diverse tasks but often struggle to accurately gauge their knowledge boundaries, leading to confident yet incorrect responses.
The Mirage of Model Editing: Revisiting Evaluation in the Wild
Our analysis provides a fundamental reexamination of both the real-world applicability of existing model editing methods and their evaluation practices, and establishes a rigorous evaluation framework with key insights to advance reliable and practical model editing research.
Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos
Video information retrieval remains a fundamental approach for accessing video content.
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs).
Generative Retrieval for Book search
Directly applying GR to book search is a challenge due to the unique characteristics of book search: The model needs to retain the complex, multi-faceted information of the book, which increases the demand for labeled data.
On the Robustness of Generative Information Retrieval Models
Based on this taxonomy, we conduct empirical studies to analyze the OOD robustness of representative generative IR models against dense retrieval models.
Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models
Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance.
Fact-Level Confidence Calibration and Self-Correction
Confidence calibration in LLMs, i. e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs.
AlignXIE: Improving Multilingual Information Extraction by Cross-Lingual Alignment
Empirical evidence suggests that LLMs exhibit spontaneous cross-lingual alignment.
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks.
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robustness of Collaborative Filtering (CF) recommender systems against poisoning attacks.
Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input.
Ranked #218 on
Visual Question Answering
on MM-Vet
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models.
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or sensitive information.
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
In this paper, we introduce a novel TDA method called Debias and Denoise Attribution (DDA), which enhances influence functions by addressing fitting errors.
Generative Retrieval Meets Multi-Graded Relevance
GR$^2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training.
Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
Leveraging these insights, we introduce the Vulnerability-aware Adversarial Training (VAT), designed to defend against poisoning attacks in recommender systems.
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
Our research identifies two critical latent factors affecting RAG's confidence in its predictions: the quality of the retrieved results and the manner in which these results are utilized.
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method
We have developed a Chinese-language benchmark, PatentMIA, to assess the performance of detection approaches for LLMs on Chinese text.
LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs
Moreover, for NF questions that do not have multi-grade or any golden answers, we leverage LLMs to generate the reference answer list of various quality to facilitate the listwise evaluation.
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
To achieve such ideal question-answering systems, locating and then editing outdated knowledge in the natural language outputs is a general target of popular knowledge editing methods.
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities.
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks.
Look Globally and Reason: Two-stage Path Reasoning over Sparse Knowledge Graphs
The sparse KG completion task, which reasons answers for given queries in the form of (head entity, relation, ?)
Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval
Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query.
Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective
Recent advances in neural information retrieval (IR) models have significantly enhanced their effectiveness over various IR tasks.
Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
As Large Language Models (LLMs) become an important way of information seeking, there have been increasing concerns about the unethical content LLMs may generate.
ALiiCE: Evaluating Positional Fine-grained Citation Generation
Large Language Models (LLMs) can enhance the credibility and verifiability by generating text with citations.
Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
The parametric knowledge memorized by large language models (LLMs) becomes outdated quickly.
Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy
Utility and topical relevance are critical measures in information retrieval (IR), reflecting system and user perspectives, respectively.
Edge Classification on Graphs: New Directions in Topological Imbalance
Our empirical studies confirm that TE effectively measures local class distribution variance, and indicate that prioritizing edges with high TE values can help address the issue of topological imbalance.
"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak
"Jailbreak" is a major safety concern of Large Language Models (LLMs), which occurs when malicious prompts lead LLMs to produce harmful outputs, raising issues about the reliability and safety of LLMs.
A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
Based on our theory, we propose a practical novel method, Tok-RAG, which achieves collaborative generation between the pure LLM and RAG at token level to preserve benefit and avoid detriment.
Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
Graph contrastive learning (GCL), standing as the dominant paradigm in the realm of graph pre-training, has yielded considerable progress.
Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
Firstly, in the layer dimension, we propose non-local block key-value storage to replace local layer key-value storage, increasing the representation ability of key-value pairs and incorporating attention layer knowledge.
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
We observe that despite a significant boost in logits of the new knowledge, the performance of is still hindered by stubborn knowledge.
Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation
With the rapid advancement of large language models (LLMs) for handling complex language tasks, an increasing number of studies are employing LLMs as agents to emulate the sequential decision-making processes of humans often represented as Markov decision-making processes (MDPs).
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
However, limiting perturbations to a single level of granularity may reduce the flexibility of adversarial examples, thereby diminishing the potential threat of the attack.
Selective Temporal Knowledge Graph Reasoning
Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently.
Class-Incremental Few-Shot Event Detection
Therefore, this paper proposes a new task, called class-incremental few-shot event detection.
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
We first revisit the current factuality enhancement methods and evaluate their effectiveness in enhancing factual accuracy.
Are Large Language Models Good at Utility Judgments?
Retrieval-augmented generation (RAG) is considered to be a promising approach to alleviate the hallucination issue of large language models (LLMs), and it has received widespread attention from researchers recently.
Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent
For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action.
Listwise Generative Retrieval Models via a Sequential Learning Process
Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the $i$-th docid given the (preceding) top $i-1$ docids.
KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction
After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to $\textbf{12. 5%}$ and $\textbf{21. 9%}$, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively.
Ranked #1 on
UIE
on ACE 2005-EAE
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval.
CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance.
Qsnail: A Questionnaire Dataset for Sequential Question Generation
Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure.
Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement
We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task.
MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning
Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge.
Event-aware Video Corpus Moment Retrieval
Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural language query.
Stable Knowledge Editing in Large Language Models
The premise of localization results in an incomplete knowledge editing, whereas an isolated assumption may impair both other knowledge and general abilities.
When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
This motivates us to enhance the LLMs' ability to perceive their knowledge boundaries to help RA.
Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models
A careful and balanced integration of the parametric knowledge within LLMs with external information is crucial to alleviate hallucinations.
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
In this work, we reveal a critical phenomenon: even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks.
Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?
In this study, we present the first comprehensive analysis of how the order of graph descriptions impacts LLM performance.
A Unified Causal View of Instruction Tuning
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
First, it is hard to share the contextual information of the ranking list between the two tasks.
Graph Domain Adaptation: Challenges, Progress and Prospects
To the best of our knowledge, this paper is the first survey for graph domain adaptation.
LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks
Traditional defense strategies predominantly depend on predefined assumptions or rules extracted from specific known attacks, limiting their generalizability to unknown attack types.
LPNL: Scalable Link Prediction with Large Language Models
This work focuses on the link prediction task and introduces $\textbf{LPNL}$ (Link Prediction via Natural Language), a framework based on large language models designed for scalable link prediction on large-scale heterogeneous graphs.
SLANG: New Concept Comprehension of Large Language Models
The dynamic nature of language, particularly evident in the realm of slang and memes on the Internet, poses serious challenges to the adaptability of large language models (LLMs).
Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from external sources.
Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning
MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets.
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
We decompose the robust ranking error into two components, i. e., a natural ranking error for effectiveness evaluation and a boundary ranking error for assessing adversarial robustness.
RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication.
A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval
Dense retrieval methods have been mostly focused on unstructured text and less attention has been drawn to structured data with various aspects, e. g., products with aspects such as category and brand.
TEA: Test-time Energy Adaptation
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images
Furthermore, our subsequent exploration reveals that the inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias.
Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue
The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses.
CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval
The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently.
Retrieval-Augmented Code Generation for Universal Information Extraction
Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks.
Plot Retrieval as an Assessment of Abstract Semantic Association
Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots.
An In-Context Schema Understanding Method for Knowledge Base Question Answering
The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base.
CIR at the NTCIR-17 ULTRE-2 Task
The Chinese academy of sciences Information Retrieval team (CIR) has participated in the NTCIR-17 ULTRE-2 task.
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification
We argue that, rather than relevance, for FV we need to focus on the utility that a claim verifier derives from the retrieved evidence.
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling
It encodes the text corpus into a latent space, capturing current and future information from both source and target text.
Causality and Independence Enhancement for Biased Node Classification
Most existing methods that address out-of-distribution (OOD) generalization for node classification on graphs primarily focus on a specific type of data biases, such as label selection bias or structural bias.
Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently.
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
Despite the widespread belief that low-degree nodes exhibit poorer LP performance, our empirical findings provide nuances to this viewpoint and prompt us to propose a better metric, Topological Concentration (TC), based on the intersection of the local subgraph of each node with the ones of its neighbors.
A Comparative Study of Training Objectives for Clarification Facet Generation
In this paper, we aim to conduct a systematic comparative study of various types of training objectives, with different properties of not only whether it is permutation-invariant but also whether it conducts sequential prediction and whether it can control the count of output facets.
Nested Event Extraction upon Pivot Element Recogniton
Since existing NEE datasets (e. g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest.
ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction
To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations.
Robust Recommender System: A Survey and Future Directions
With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload.
A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications
Despite this progress, there is a lack of a comprehensive overview of the attacks and the techniques for preserving privacy in the graph domain.
Continual Learning for Generative Retrieval over Dynamic Corpora
We put forward a novel Continual-LEarner for generatiVE Retrieval (CLEVER) model and make two major contributions to continual learning for GR: (i) To encode new documents into docids with low computational cost, we present Incremental Product Quantization, which updates a partial quantization codebook according to two adaptive thresholds; and (ii) To memorize new documents for querying without forgetting previous knowledge, we propose a memory-augmented learning mechanism, to form meaningful connections between old and new documents.
Inducing Causal Structure for Abstractive Text Summarization
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations
First-stage retrieval is a critical task that aims to retrieve relevant document candidates from a large-scale collection.
Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method
The AREA task is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model in response to a query.
Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
Transfer learning has been a feasible way to transfer knowledge from high-quality external data of source domains to limited data of target domains, which follows a domain-level knowledge transfer to learn a shared posterior distribution.
OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learning
Overall, OpenGDA provides a user-friendly, scalable and reproducible benchmark for evaluating graph domain adaptation models.
On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective
Recently, we have witnessed generative retrieval increasingly gaining attention in the information retrieval (IR) field, which retrieves documents by directly generating their identifiers.
PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
IDEA: Invariant Defense for Graph Adversarial Robustness
To address these limitations, we analyze the causalities in graph adversarial attacks and conclude that causal features are key to achieve graph adversarial robustness, owing to their determinedness for labels and invariance across attacks.
LLMDet: A Third Party Large Language Models Generated Text Detection Tool
By jointly analyzing the proxy perplexities of LLMs, we can determine the source of the generated text.
Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning.
Semantic Structure Enhanced Event Causality Identification
This is a very challenging task, because causal relations are usually expressed by implicit associations between events.
SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation
Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue.
BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
Few-shot Link Prediction on N-ary Facts
Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs).
Popularity Debiasing from Exposure to Interaction in Collaborative Filtering
In this paper, we propose a new criterion for popularity debiasing, i. e., in an unbiased recommender system, both popular and unpopular items should receive Interactions Proportional to the number of users who Like it, namely IPL criterion.
Visual Transformation Telling
Humans can naturally reason from superficial state differences (e. g. ground wetness) to transformations descriptions (e. g. raining) according to their life experience.
Visual Reasoning: from State to Transformation
Such \textbf{state driven} visual reasoning has limitations in reflecting the ability to infer the dynamics between different states, which has shown to be equally important for human cognition in Piaget's theory.
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
This paper proposes a novel framework named \textbf{Search-in-the-Chain} (SearChain) for the interaction between LLM and IR to solve the challenges.
Ranked #2 on
Question Answering
on StrategyQA
(EM metric)
A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning
Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic granularity, such as a document retriever, passage retriever, sentence retriever, and entity retriever, may help to achieve better performance on the end-to-end task.
Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models
In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic.
Graph Adversarial Immunization for Certifiable Robustness
In this paper, we propose and formulate graph adversarial immunization, i. e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack.
Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation
To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance.
Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network
To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes.
Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks
However, most nodes in the tribe-style graph lack attributes, making it difficult to directly adopt existing graph learning methods (e. g., Graph Neural Networks(GNNs)).
Multi-video Moment Ranking with Multimodal Clue
In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference.
Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
Comparative loss is essentially a ranking loss on top of the task-specific losses of the full and ablated models, with the expectation that the task-specific loss of the full model is minimal.
Rich Event Modeling for Script Event Prediction
Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants.
NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework
Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts.
Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks.
Visual Named Entity Linking: A New Dataset and A Baseline
Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i. e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL).
LegoNet: A Fast and Exact Unlearning Architecture
However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance.
DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years.
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning
This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps.
Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
A ranking model is said to be Certified Top-$K$ Robust on a ranked list when it is guaranteed to keep documents that are out of the top $K$ away from the top $K$ under any attack.
Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models
When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the learned NRM becomes even worse.
Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval
Unlike the promising results in NLP, we find that these methods cannot achieve comparable performance to full fine-tuning at both stages when updating less than 1\% of the original model parameters.
A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval
Empirical results show that our method can significantly outperform the state-of-the-art autoencoder-based language models and other pre-trained models for dense retrieval.
CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks
We show that a strong generative retrieval model can be learned with a set of adequately designed pre-training tasks, and be adopted to improve a variety of downstream KILT tasks with further fine-tuning.
Adversarial Camouflage for Node Injection Attack on Graphs
In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes.
Learning node embeddings via summary graphs: a brief theoretical analysis
Recent works try to improve scalability via graph summarization -- i. e., they learn embeddings on a smaller summary graph, and then restore the node embeddings of the original graph.
Few-Shot Stance Detection via Target-Aware Prompt Distillation
The main challenge of this task comes two-fold: few-shot learning resulting from the varying targets and the lack of contextual information of the targets.
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback
Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be.
Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction
% Therefore, in this work, we propose to drop out the decoder and introduce a novel contrastive span prediction task to pre-train the encoder alone.
Multi-scale Anomaly Detection for Big Time Series of Industrial Sensors
Given a multivariate big time series, can we detect anomalies as soon as they occur?
GERE: Generative Evidence Retrieval for Fact Verification
This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead; ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking; iii) a fixed number of sentences are selected to form the final evidence set.
Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
In generalization stage, matching model explores the essential matching signals by being trained on diverse matching tasks.
PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Models
We focus on the decision-based black-box attack setting, where the attackers cannot directly get access to the model information, but can only query the target model to obtain the rank positions of the partial retrieved list.
Twin Weisfeiler-Lehman: High Expressive GNNs for Graph Classification
The expressive power of message passing GNNs is upper-bounded by Weisfeiler-Lehman (WL) test.
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.
A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty
By reducing the weights of the majority classes, such instances would become more difficult to learn and hurt the overall performance consequently.
What is Event Knowledge Graph: A Survey
Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG).
Piecing and Chipping: An effective solution for the information-erasing view generation in Self-supervised Learning
In self-supervised learning frameworks, deep networks are optimized to align different views of an instance that contains the similar visual semantic information.
Integrating Deep Event-Level and Script-Level Information for Script Event Prediction
In this paper, we propose a Transformer-based model, called MCPredictor, which integrates deep event-level and script-level information for script event prediction.
Transductive Learning for Unsupervised Text Style Transfer
The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
Adaptive Information Seeking for Open-Domain Question Answering
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus.
Ranked #3 on
Question Answering
on HotpotQA
Single Node Injection Attack against Graph Neural Networks
In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i. e., the attacker is only allowed to inject one single node during the test phase to hurt GNN's performance.
Signed Bipartite Graph Neural Networks
Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets.
Toward the Understanding of Deep Text Matching Models for Information Retrieval
We further extend these constraints to the semantic settings, which are shown to be better satisfied for all the deep text matching models.
Are Neural Ranking Models Robust?
So we raise the question in this work: Are neural ranking models robust?
FedMatch: Federated Learning Over Heterogeneous Question Answering Data
A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets.
Conditional GANs with Auxiliary Discriminative Classifier
Specifically, the proposed auxiliary discriminative classifier becomes generator-aware by recognizing the class-labels of the real data and the generated data discriminatively.
Ranked #1 on
Conditional Image Generation
on Tiny ImageNet
A Discriminative Semantic Ranker for Question Retrieval
However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance.
INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
INMO generates the inductive embeddings for users (items) by characterizing their interactions with some template items (template users), instead of employing an embedding lookup table.
Self-Supervised GANs with Label Augmentation
Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment.
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts.
Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity).
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval
The basic idea of PROP is to construct the \textit{representative words prediction} (ROP) task for pre-training inspired by the query likelihood model.
Locate Who You Are: Matching Geo-location to Text for User Identity Linkage
However, encouraged by online services, users would also post asymmetric information across networks, such as geo-locations and texts.
Sketch and Customize: A Counterfactual Story Generator
In the sketch stage, a skeleton is extracted by removing words which are conflict to the counterfactual condition, from the original ending.
GCN-ALP: Addressing Matching Collisions in Anchor Link Prediction
However, the low quality of observed user data confuses the judgment on anchor links, resulting in the matching collision problem in practice.
Semantic Models for the First-stage Retrieval: A Comprehensive Review
We believe it is the right time to survey current status, learn from existing methods, and gain some insights for future development.
A Linguistic Study on Relevance Modeling in Information Retrieval
We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question.
Learning to Truncate Ranked Lists for Information Retrieval
One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search.
Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
However, these models designed for short texts cannot well address the long-form text matching problem, because there are many contexts in long-form texts can not be directly aligned with each other, and it is difficult for existing models to capture the key matching signals from such noisy data.
Modelling Universal Order Book Dynamics in Bitcoin Market
Understanding the emergence of universal features such as the stylized facts in markets is a long-standing challenge that has drawn much attention from economists and physicists.
SDGNN: Learning Node Representation for Signed Directed Networks
Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.
Towards Powerful Graph Neural Networks: Diversity Matters
For a target node, diverse sampling offers it diverse neighborhoods, i. e., rooted sub-graphs, and the representation of target node is finally obtained via aggregating the representation of diverse neighborhoods obtained using any GNN model.
Slimmable Generative Adversarial Networks
In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.
AugSplicing: Synchronized Behavior Detection in Streaming Tensors
Therefore, we propose a fast streaming algorithm, AugSplicing, which can detect the top dense blocks by incrementally splicing the previous detection with the incoming ones in new tuples, avoiding re-runs over all the history data at every tracking time step.
Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings
To resolve event coreference, existing methods usually calculate the similarities between event mentions and between specific kinds of event arguments.
Transformation Driven Visual Reasoning
Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i. e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views).
PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval
Recently pre-trained language representation models such as BERT have shown great success when fine-tuned on downstream tasks including information retrieval (IR).
Summarizing graphs using configuration model
As a solution, graph summarization, which aims to find a compact representation that preserves the important properties of a given graph, has received much attention, and numerous algorithms have been developed for it.
Social and Information Networks
Beyond Language: Learning Commonsense from Images for Reasoning
This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP.
DeepHawkes: Bridging the gap between prediction and understanding of information cascades
In this paper, we propose DeepHawkes to combat the defects of existing methods, leveraging end-to-end deep learning to make an analogy to interpretable factors of Hawkes process — a widely-used generative process to model information cascade.
Statistical Consistency of Ranking Methods in A Rank-Differentiable Probability Space
This paper is concerned with the statistical consistency of ranking methods.
