* 共同第一作者；† 通讯作者。
第一作者论文
Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
NeuroCogMap Reveals Cognitive Organization of Large Language Models
Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models
ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
LargePiG: Your Large Language Model is Secretly a Pointer Generator
ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
Large Language Models Enhanced Collaborative Filtering
Effective In-Context Example Selection through Data Compression
To Search or to Recommend: Predicting Open-App Motivation with Neural Hawkes Process
Logic Rules as Explanations for Legal Case Retrieval
KuaiSAR: A Unified Search And Recommendation Dataset
Explainable Legal Case Matching via Graph Optimal Transport
Law Article-Enhanced Legal Case Matching: a Causal Learning Approach
其他已发表或已接收论文
DLLM-Searcher: Adapting Diffusion Language Model for Efficient Search Agents
Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering
Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamic Mechanisms and Efficient Alignment
基于多智能体协作的检索增强生成可归因拒答方法
QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs
StyliTruth: Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
Empowering Open-Domain LLMs for Legal Document Correction via Legal Knowledge Integration and Decoding Constraints
Trustworthy Information Retrieval in the LLM Era: Bias, Unfairness, and Hallucination
SyLeR: A Framework for Explicit Syllogistic Legal Reasoning in Large Language Models
LLM-Empowered Creator Simulation for Long-Term Evaluation of Recommender Systems under Information Asymmetry
Trigger3: Refining Query Correction via Adaptive Model Selector
Generative Retrieval with Semantic Tree-Structured Identifiers and Contrastive Learning
TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou
Uncovering ChatGPT's Capabilities in Recommender Systems
When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
Enhancing Recommendation with Search Data in a Causal Learning Manner
Enough Waiting for the Couriers: Learning to Estimate Package Pick-up Arrival Time from Couriers’ Spatial-Temporal Behaviors
Explainable Legal Case Matching via Inverse Optimal Transport-Based Rationale Extraction
AddrMiner: A Comprehensive Global Active IPv6 Address Discovery System
预印本
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios
Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
Memory in the Age of AI Agents
A Survey of Large Language Models for Law: Task Capabilities, Authority Grounding, and System Governance