59 citations · 142 across the 51 of their papers we have counts for
54 papers
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents
Yutao Mou, Pengfei Yang, Zhe Yin +6
Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely re…
SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval
Yuxiao Luo, Da Li, Mingjie Zhang +3
LLM-based retrievers have become a fundamental component of modern information retrieval systems. The paradigm of "rewrite-then-retriev" introduces explicit reasoning before retrie…
Data Selection for Multi-turn Dialogue Instruction Tuning
Bo Li, Shikun Zhang, Wei Ye
Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repeti…
GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
Zhuoyao Liu, Zhengran Zeng, Shu-Dong Huang +3
Large Language Model (LLM)-based Automated Program Repair (APR) has shown strong potential on textual benchmarks, yet struggles in multimodal scenarios where bugs are reported with…
An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
Chengli Xing, Zhengran Zeng, Gexiang Fang +3
Recent advancements in code large language models (Code-LLMs) have demonstrated remarkable capabilities in resolving programming related tasks. Meanwhile, researchers have recogniz…
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
Zhen Ye, Xu Tan, Aoxiong Yin +8
Joint audio-video generation models have shown that unified generation yields stronger cross-modal coherence than cascaded approaches. However, existing models couple modalities th…
SteerRM: Debiasing Reward Models via Sparse Autoencoders
Mengyuan Sun, Zhuohao Yu, Weizheng Gu +2
Reward models (RMs) are critical components of alignment pipelines, yet they exhibit biases toward superficial stylistic cues, preferring better-presented responses over semantical…
OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration
Qi Guo, Jianing Wang, Deyang Kong +7
Parallel thinking has emerged as a new paradigm for large reasoning models (LRMs) in tackling complex problems. Recent methods leverage Reinforcement Learning (RL) to enhance paral…
What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?
Weizheng Gu, Chengze Li, Zhuohao Yu +6
Large language models are increasingly evaluated as interactive agents, yet standard agent benchmarks conflate two qualitatively distinct sources of success: semantic tool-use and…
Adaptive Test-Time Compute Allocation for Block Diffusion Language Models in Complex Reasoning
Yi Lu, Deyang Kong, Jianing Wang +8
Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, their test-time compute allocation…
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…
Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
Bo Li, Tian Tian, Zhenghua Xu +3
Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central cha…
Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development
Zhengran Zeng, Yixin Li, Rui Xie +2
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluati…
Decoupling Safety into Orthogonal Subspace: Cost-Efficient and Performance-Preserving Alignment for Large Language Models
Yutao Mou, Xiaoling Zhou, Yuxiao Luo +2
Safety alignment is essential for building trustworthy artificial intelligence, yet it remains challenging to enhance model safety without degrading general performance. Current ap…
AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
Muxi Diao, Yutao Mou, Keqing He +6
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits…
Autoformalizer with Tool Feedback
Qi Guo, Jianing Wang, Jianfei Zhang +8
Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in r…
TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
Yidong Wang, Yunze Song, Tingyuan Zhu +11
The adoption of Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks. We identify two fundam…
SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation
Zhengran Zeng, Ruikai Shi, Keke Han +7
Automated Code Review (ACR) is crucial for software quality, yet existing benchmarks often fail to reflect real-world complexities, hindering the evaluation of modern Large Languag…
SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
Zhuohao Yu, Xingru Jiang, Weizheng Gu +4
Watermarking LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access…
Seed&Steer: Guiding Large Language Models with Compilable Prefix and Branch Signals for Unit Test Generation
Shuaiyu Zhou, Zhengran Zeng, Xiaoling Zhou +3
Unit tests play a vital role in the software development lifecycle. Recent advances in Large Language Model (LLM)-based approaches have significantly improved automated test genera…
VLM-R: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
Chaoya Jiang, Yongrui Heng, Wei Ye +6
Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate…
MPL: Multiple Programming Languages with Large Language Models for Information Extraction
Bo Li, Gexiang Fang, Wei Ye +4
Recent research in information extraction (IE) focuses on utilizing code-style inputs to enhance structured output generation. The intuition behind this is that the programming lan…
Mitigating Spurious Correlations with Causal Logit Perturbation
Xiaoling Zhou, Wei Ye, Rui Xie +1
Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness,…
Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective
Yutao Mou, Xiao Deng, Yuxiao Luo +2
Code security and usability are both essential for various coding assistant applications driven by large language models (LLMs). Current code security benchmarks focus solely on si…