Search Results for author:
Found 90 papers, 55 papers with code
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching
Enjoying the partial transport properties of OPT, the selected key sentences can not only effectively enhance the matching accuracy, but also be explained as the rationales for the matching results.
Understanding Accuracy-Fairness Trade-offs in Re-ranking through Elasticity in Economics
Prior work has identified a trade-off between ranking accuracy and item fairness.
LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph
Next, through a Transformer-based Knowledge Adapter, it finely extracts and integrates factual and structural information from the KG, then maps this information to the LLM's token embedding space, creating an LLM-friendly prompt to be used by the LLM for the final reasoning.
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
In this paper, we explain the process of information retrieval with a causal graph and discover that PLM-based retrievers learn perplexity features for relevance estimation, causing source bias by ranking the documents with low perplexity higher.
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.
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools.
FineFilter: A Fine-grained Noise Filtering Mechanism for Retrieval-Augmented Large Language Models
We optimize each module to tackle complex reasoning challenges: (1) Clue extractor firstly uses sentences containing the answer and similar ones as fine-tuned targets, aiming at extracting sufficient potential clues; (2) Re-ranker is trained to prioritize effective clues based on the real feedback from generation module, with clues capable of generating correct answer as positive samples and others as negative; (3) Truncator takes the minimum clues needed to answer the question (truncation point) as fine-tuned targets, and performs truncation on the re-ranked clues to achieve fine-grained noise filtering.
Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
To overcome these limitations, we first theoretically demonstrate that the MMF-constrained objective can be essentially reformulated as a group-weighted optimization objective.
Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos
Video information retrieval remains a fundamental approach for accessing video content.
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 #220 on
Visual Question Answering
on MM-Vet
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.
AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
Specifically, we first annotate the minimum top-k documents necessary for the RAG system to answer the current query as the compression rate and then construct triplets of the query, retrieved documents, and its compression rate.
MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models
Inspired by RLAIF, we train three kinds of reward models for the above metrics to achieve more efficient training.
A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
Grounding external knowledge can enhance the factuality of responses in dialogue generation.
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.
Source Echo Chamber: Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop
How and to what extent the source bias affects the neural recommendation models within feedback loop remains unknown.
Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content.
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.
A Survey of Generative Search and Recommendation in the Era of Large Language Models
With the information explosion on the Web, search and recommendation are foundational infrastructures to satisfying users' information needs.
Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era
With the rapid advancements of large language models (LLMs), information retrieval (IR) systems, such as search engines and recommender systems, have undergone a significant paradigm shift.
Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
Their ability to execute intricate compositional reasoning tasks is also constrained, culminating in a stagnation of learning progression for these models.
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.
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.
Thermal-NeRF: Neural Radiance Fields from an Infrared Camera
In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit representation for 3D scene reconstruction.
Beyond Memorization: The Challenge of Random Memory Access in Language Models
Through carefully-designed synthetic tasks, covering the scenarios of full recitation, selective recitation and grounded question answering, we reveal that LMs manage to sequentially access their memory while encountering challenges in randomly accessing memorized content.
Can Small Language Models be Good Reasoners for Sequential Recommendation?
We encode the generated rationales from the student model into a dense vector, which empowers recommendation in both ID-based and ID-agnostic scenarios.
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.
GraphEdit: Large Language Models for Graph Structure Learning
Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data by generating novel graph structures.
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.
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.
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.
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.
SCTc-TE: A Comprehensive Formulation and Benchmark for Temporal Event Forecasting
Temporal complex event forecasting aims to predict the future events given the observed events from history.
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.
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks.
De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks.
A Study of Implicit Ranking Unfairness in Large Language Models
Worse still, in this paper, we identify a subtler form of discrimination in LLMs, termed \textit{implicit ranking unfairness}, where LLMs exhibit discriminatory ranking patterns based solely on non-sensitive user profiles, such as user names.
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.
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.
Neural Retrievers are Biased Towards LLM-Generated Content
Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher.
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.
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context.
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.
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.
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)
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.
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.
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.
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.
Uncertainty Calibration for Ensemble-Based Debiasing Methods
Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target.
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
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.
Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm
Experimental results base on three publicly available benchmarks showed that in both of the implementations, Pre-Rank can respectively outperform the underlying ranking models and achieved state-of-the-art performances.
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.
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.
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation
However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient.
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).
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
Four popular text matching methods have been exploited in the paper.
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.
Modeling Topical Relevance for Multi-Turn Dialogue Generation
Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly.
Ranking Enhanced Dialogue Generation
To tackle this problem, we propose a Ranking Enhanced Dialogue generation framework in this paper.
Robust Reinforcement Learning with Wasserstein Constraint
Robust Reinforcement Learning aims to find the optimal policy with some extent of robustness to environmental dynamics.
L2R2: Leveraging Ranking for Abductive Reasoning
To fill this gap, we switch to a ranking perspective that sorts the hypotheses in order of their plausibilities.
SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval
In learning-to-rank for information retrieval, a ranking model is automatically learned from the data and then utilized to rank the sets of retrieved documents.
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
Then, the self-attention mechanism is utilized to update both the context and masked response representation.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
However, the performances of such models are not so good as that in the RC task.
Continual Match Based Training in Pommerman: Technical Report
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
Locally Smoothed Neural Networks
The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields.
DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval
This paper concerns a deep learning approach to relevance ranking in information retrieval (IR).
A Deep Investigation of Deep IR Models
Therefore, it is necessary to identify the difference between automatically learned features by deep IR models and hand-crafted features used in traditional learning to rank approaches.
MatchZoo: A Toolkit for Deep Text Matching
In recent years, deep neural models have been widely adopted for text matching tasks, such as question answering and information retrieval, showing improved performance as compared with previous methods.
A Study of MatchPyramid Models on Ad-hoc Retrieval
Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it.
Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i. e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position.
Text Matching as Image Recognition
An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score.
A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
Our model has several advantages: (1) By using Bi-LSTM, rich context of the whole sentence is leveraged to capture the contextualized local information in each positional sentence representation; (2) By matching with multiple positional sentence representations, it is flexible to aggregate different important contextualized local information in a sentence to support the matching; (3) Experiments on different tasks such as question answering and sentence completion demonstrate the superiority of our model.
Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform
This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.
Combination of Diverse Ranking Models for Personalized Expedia Hotel Searches
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.
