124 citations · 152 across the 22 of their papers we have counts for
22 papers
RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
Shicheng Xu, Liang Pang, Liyi Chen +7
Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic…
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
Zihao Wei, Wenjie Shi, Liang Pang +8
Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We…
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Jingcheng Deng, Zihao Wei, Liang Pang +4
Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reason…
SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement
Zenghao Duan, Yuxin Tian, Zhiyi Yin +6
LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to t…
Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models
Zenghao Duan, Liang Pang, Zihao Wei +6
Despite the success of test-time scaling, Large Reasoning Models (LRMs) frequently encounter repetitive loops that lead to computational waste and inference failure. In this paper,…
LLM Latent Reasoning as Chain of Superposition
Jingcheng Deng, Liang Pang, Zihao Wei +6
Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chai…
Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model
Shicheng Xu, Xin Huang, Zihao Wei +3
Full-process clinical diagnosis in the real world encompasses the entire diagnostic workflow that begins with only an ambiguous chief complaint. While artificial intelligence (AI),…
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
Zihao Wei, Liang Pang, Jiahao Liu +7
Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reaso…
RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
Shicheng Xu, Liang Pang, Yunchang Zhu +6
Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models…
Generative Ghost: Investigating Ranking Bias Hidden in AI-Generated Videos
Haowen Gao, Liang Pang, Shicheng Xu +4
With the rapid development of AI-generated content (AIGC), the creation of high-quality AI-generated videos has become faster and easier, resulting in the Internet being flooded wi…
Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Shicheng Xu, Liang Pang, Yunchang Zhu +2
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment met…
A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
Shicheng Xu, Liang Pang, Huawei Shen +1
Retrieval-augmented generation (RAG) utilizes retrieved texts to enhance large language models (LLMs). Studies show that while RAG provides valuable external information (benefit),…
Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era
Sunhao Dai, Chen Xu, Shicheng Xu +3
With the rapid advancements of large language models (LLMs), information retrieval (IR) systems, such as search engines and recommender systems, have undergone a significant paradi…
List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
Shicheng Xu, Liang Pang, Jun Xu +2
The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generatio…
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
Shicheng Xu, Liang Pang, Mo Yu +4
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face…
Plot Retrieval as an Assessment of Abstract Semantic Association
Shicheng Xu, Liang Pang, Jiangnan Li +5
Retrieving relevant plots from the book for a query is a critical task, which can improve the reading experience and efficiency of readers. Readers usually only give an abstract an…
Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images
Shicheng Xu, Danyang Hou, Liang Pang +4
With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source…
Multi-task 3D building understanding with multi-modal pretraining
Shicheng Xu
This paper explores various learning strategies for 3D building type classification and part segmentation on the BuildingNet dataset. ULIP with PointNeXt and PointNeXt segmentation…
BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval
Shicheng Xu, Liang Pang, Huawei Shen +1
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. However, previous studies have found that dense retrieval is hard…
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
Shicheng Xu, Liang Pang, Huawei Shen +2
Making the content generated by Large Language Model (LLM), accurate, credible and traceable is crucial, especially in complex knowledge-intensive tasks that require multi-step rea…
NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework
Shicheng Xu, Liang Pang, Huawei Shen +1
Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain que…
Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
Shicheng Xu, Liang Pang, Huawei Shen +1
Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship…