Search Results for author:
Found 180 papers, 86 papers with code
Semantic Sentence Matching via Interacting Syntax Graphs
In this paper, we formalize the task of semantic sentence matching as a problem of graph matching in which each sentence is represented as a directed graph according to its syntactic structures.
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.
ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis
Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability.
Length-Induced Embedding Collapse in Transformer-based Models
In this paper, we find that the performance degradation is due to a phenomenon called Length Collapse, where longer text embeddings collapse into a narrow space.
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
We discover hallucinations occur when the Knowledge FFNs in LLMs overemphasize parametric knowledge in the residual stream, while Copying Heads fail to effectively retain or integrate external knowledge from retrieved content.
LargePiG: Your Large Language Model is Secretly a Pointer Generator
To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios.
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data.
Enhancing Sequential Recommendations through Multi-Perspective Reflections and Iteration
Specifically, MoRE introduces three reflectors for generating LLM-based reflections on explicit preferences, implicit preferences, and collaborative signals.
Length Desensitization in Direct Preference Optimization
Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy.
KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications.
AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results
The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H. 264, HEVC/H. 265, AV1, and VVC/H. 266) and containing a comprehensive collection of compression artifacts.
Revisiting Reciprocal Recommender Systems: Metrics, Formulation, and Method
By utilizing the potential outcome framework, we further develop a model-agnostic causal reciprocal recommendation method that considers the causal effects of recommendations.
Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution
The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales.
Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation
In this paper, we propose $\text{Transition}^2$, a novel method to model transitions across both domains and types of user feedback.
Towards Effective and Efficient Continual Pre-training of Large Language Models
To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model.
Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning
In recent years, graph contrastive learning (GCL) has received increasing attention in recommender systems due to its effectiveness in reducing bias caused by data sparsity.
A Survey of Controllable Learning: Methods and Applications in Information Retrieval
Controllable learning (CL) emerges as a critical component in trustworthy machine learning, ensuring that learners meet predefined targets and can adaptively adjust without retraining according to the changes in those targets.
YuLan: An Open-source Large Language Model
This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters.
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters.
Do Not Wait: Learning Re-Ranking Model Without User Feedback At Serving Time in E-Commerce
It means the modification is tailored to and only to the current request to capture the specific context of the request.
Counteracting Duration Bias in Video Recommendation via Counterfactual Watch Time
In video recommendation, an ongoing effort is to satisfy users' personalized information needs by leveraging their logged watch time.
QAGCF: Graph Collaborative Filtering for Q&A Recommendation
Traditional recommendation methods treat the question-answer pair as a whole or only consider the answer as a single item, which overlooks the two challenges and cannot effectively model user interests.
Efficient Knowledge Infusion via KG-LLM Alignment
To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion.
SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information
This allows a higher update frequency, thereby enhancing accuracy by enabling the updated parameters to more closely mimic full-rank behavior during the pre-training phase.
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.
Tool Learning with Large Language Models: A Survey
In this survey, we focus on reviewing existing literature from the two primary aspects (1) why tool learning is beneficial and (2) how tool learning is implemented, enabling a comprehensive understanding of tool learning with LLMs.
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.
ReCODE: Modeling Repeat Consumption with Neural ODE
In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly.
Guaranteeing Accuracy and Fairness under Fluctuating User Traffic: A Bankruptcy-Inspired Re-ranking Approach
Previous studies often show that the two sides' needs show different urgency: providers need a relatively long-term exposure demand while users want more short-term and accurate service.
Towards Completeness-Oriented Tool Retrieval for Large Language Models
Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions, frequently leading to the retrieval of redundant, similar tools.
Ranked #1 on
Retrieval
on ToolLens
Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging
The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent.
Effective In-Context Example Selection through Data Compression
In this paper, we propose a data compression approach to the selection of in-context examples.
Variational Neuron Shifting for Few-Shot Image Classification Across Domains
Existing meta-learning models learn the ability of learning good representation or model parameters, in order to adapt to new tasks with a few training samples.
Masked Latent Transformer with the Random Masking Ratio to Advance the Diagnosis of Dental Fluorosis
To advance the diagnosis of dental fluorosis, we propose a pioneering deep learning model called masked latent transformer with the random masking ratio (MLTrMR).
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.
UniSAR: Modeling User Transition Behaviors between Search and Recommendation
In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service.
Pathological Primitive Segmentation Based on Visual Foundation Model with Zero-Shot Mask Generation
Primitive detection and segmentation in digitized tissue samples are essential for objective and automated diagnosis and prognosis of cancer.
Nonlinear Kalman Filtering based on Self-Attention Mechanism and Lattice Trajectory Piecewise Linear Approximation
The traditional Kalman filter (KF) is widely applied in control systems, but it relies heavily on the accuracy of the system model and noise parameters, leading to potential performance degradation when facing inaccuracies.
To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process
The model, referred to as Neural Hawkes Process-based Open-App Motivation prediction model (NHP-OAM), employs a hierarchical transformer and a novel intensity function to encode multiple factors, and open-app motivation prediction layer to integrate time and user-specific information for predicting users' open-app motivations.
Modeling Output-Level Task Relatedness in Multi-Task Learning with Feedback Mechanism
Multi-task learning (MTL) is a paradigm that simultaneously learns multiple tasks by sharing information at different levels, enhancing the performance of each individual task.
Large Language Models Enhanced Collaborative Filtering
In this paper, drawing inspiration from the in-context learning and chain of thought reasoning in LLMs, we propose the Large Language Models enhanced Collaborative Filtering (LLM-CF) framework, which distils the world knowledge and reasoning capabilities of LLMs into collaborative filtering.
IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History
This poses a new challenge for existing imitation learning approaches that can only utilize data from experienced experts.
OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning
Redundancy is a persistent challenge in Capsule Networks (CapsNet), leading to high computational costs and parameter counts.
Priority-based Energy Allocation in Buildings through Distributed Model Predictive Control
For the scenarios where the energy system is not sufficiently supplied to HVAC systems, a priority-based allocation scheme based on distributed model predictive control is proposed in this paper, which distributes the energy rationally based on priority order.
Lattice piecewise affine approximation of explicit model predictive control with application to satellite attitude control
Satellite attitude cotrol is a crucial part of aerospace technology, and model predictive control(MPC) is one of the most promising controllers in this area, which will be less effective if real-time online optimization can not be achieved.
ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models
This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #1 on
Visual Question Answering
on MM-Vet
Logic Rules as Explanations for Legal Case Retrieval
In this paper, we address the issue of using logic rules to explain the results from legal case retrieval.
On the Decision-Making Abilities in Role-Playing using Large Language Models
Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts.
A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection
Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades.
FairSync: Ensuring Amortized Group Exposure in Distributed Recommendation Retrieval
Specifically, FairSync resolves the issue by moving it to the dual space, where a central node aggregates historical fairness data into a vector and distributes it to all servers.
Sparsity via Sparse Group $k$-max Regularization
For the linear inverse problem with sparsity constraints, the $l_0$ regularized problem is NP-hard, and existing approaches either utilize greedy algorithms to find almost-optimal solutions or to approximate the $l_0$ regularization with its convex counterparts.
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.
AI in ESG for Financial Institutions: An Industrial Survey
The burgeoning integration of Artificial Intelligence (AI) into Environmental, Social, and Governance (ESG) initiatives within the financial sector represents a paradigm shift towards more sus-tainable and equitable financial practices.
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
In this work, we present HuixiangDou, a technical assistant powered by Large Language Models (LLM).
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA