19 papers
The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search
Peiyang Liu, Xi Wang, Di Liang +1
As Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and subop…
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
Peiyang Liu, Xi Wang, Ziqiang Cui +2
In-context learning (ICL) can induce emergent misalignment (EM), where narrow misaligned examples alter answers to unrelated questions. Existing prompts, however, conflate harmful-…
AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Ziqiang Cui, Han Shi, Bowei He +8
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several f…
Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning
Mingxuan Fan, Peiyang Liu
Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy…
Looking Farther with Confidence: Uncertainty-Guided Future Learning for Sequential Recommendation
Ziqiang Cui, Xing Tang, Peiyang Liu +4
Sequential recommendation effectively models dynamic user interests but continues to face challenges related to data sparsity. While self-supervised learning has alleviated this is…
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Peiyang Liu, Ziqiang Cui, Xi Wang +2
Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external…
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
Chao Xue, Yao Wang, Mengqiao Liu +11
Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despit…
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
Peiyang Liu, Qiang Yan, Ziqiang Cui +3
Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-maki…
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Chao Xue, Yao Wang, Mengqiao Liu +11
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after conve…
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
Zekai Lin, Chao Xue, Di Liang +8
Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-cri…
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
Peiyang Liu, Zhirui Chen, Xi Wang +4
Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches ret…
StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
Zhirui Chen, Peiyang Liu, Ling Shao
As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidt…
SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
Long Li, Zhijian Zhou, Jiangxuan Long +5
Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignme…
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Yutao Mou, Zhangchi Xue, Lijun Li +4
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation be…
Who Stole Your Data? A Method for Detecting Unauthorized RAG Theft
Peiyang Liu, Ziqiang Cui, Di Liang +1
Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) by mitigating hallucinations and outdated information issues, yet simultaneously facilitates unauthorized…
Queries Are Not Alone: Clustering Text Embeddings for Video Search
Peyang Liu, Xi Wang, Ziqiang Cui +1
The rapid proliferation of video content across various platforms has highlighted the urgent need for advanced video retrieval systems. Traditional methods, which primarily depend…
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
Xiaoyu Liu, Di Liang, Chang Dai +9
Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and backgroun…
Less Is More: Elevating RAG via Performance-Driven Context Compression
Ziqiang Cui, Yunpeng Weng, Xing Tang +7
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. Howeve…
Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
Ziqiang Cui, Yunpeng Weng, Xing Tang +8
Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive p…