148 citations · 708 across the 141 of their papers we have counts for
24 papers · 1 filter
EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce
Rui Min, Zile Qiao, Ze Xu +18
Foundation agents have rapidly advanced in their ability to reason and interact with real environments, making the evaluation of their core capabilities increasingly important. Whi…
REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation
Fulin Shi, Wenyi Xiao, Bin Chen +2
Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing e…
Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
Yuchen Wu, Liang Ding, Li Shen +1
Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge. We find that SFT-based methods,…
Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
Fei Wang, Li Shen, Liang Ding +3
Large Language Models excel at natural language processing tasks, but their massive size leads to high computational and storage demands. Recent works have sought to reduce their m…
Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
Yuchun Miao, Liang Ding, Sen Zhang +3
Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major c…
A Multi-Language Object-Oriented Programming Benchmark for Large Language Models
Shuai Wang, Liang Ding, Li Shen +4
Establishing fair and robust benchmarks is essential for evaluating intelligent code generation by large language models (LLMs). Our survey of 35 existing benchmarks uncovers three…
AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
Chunhao Tian, Yutong Wang, Xuebo Liu +4
Proper initialization is crucial for any system, particularly in multi-agent systems (MAS), where it plays a pivotal role in determining both the system's efficiency and effectiven…
Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
Yuchen Wu, Liang Ding, Li Shen +1
Large language models (LLMs) encode vast amounts of world knowledge but remain static once trained, making the timely integration of emerging facts prohibitively expensive via full…
MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism
Zheng Zhang, Donglin Yang, Yaqi Xia +4
Recently, Mixture-of-Experts (MoE) has become one of the most popular techniques to scale pre-trained models to extraordinarily large sizes. Dynamic activation of experts allows fo…
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
Yuqi Zhang, Yuchun Miao, Zuchao Li +1
We introduce AMIA, a lightweight, inference-only defense for Large Vision-Language Models (LVLMs) that (1) Automatically Masks a small set of text-irrelevant image patches to disru…
Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
Keqin Peng, Liang Ding, Yuanxin Ouyang +2
Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. Howeve…
Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning
Qihuang Zhong, Liang Ding, Fei Liao +3
Domain-specific instruction-tuning has become the defacto standard for improving the performance of large language models (LLMs) in specialized applications, e.g., medical question…
KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance
Qihuang Zhong, Liang Ding, Xiantao Cai +3
Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature rev…
Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites
Xintong Wang, Yixiao Liu, Jingheng Pan +3
Detoxifying offensive language while preserving the speaker's original intent is a challenging yet critical goal for improving the quality of online interactions. Although large la…
Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
Qingyu Lu, Liang Ding, Siyi Cao +4
Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffe…
Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation
Shizhan Cai, Liang Ding, Dacheng Tao
The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often…
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Yikun Wang, Siyin Wang, Qinyuan Cheng +5
Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typi…
Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG
Wenbin Wang, Yongcheng Jing, Liang Ding +5
High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away f…
Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
Yuchen Wu, Liang Ding, Li Shen +1
Knowledge editing allows for efficient adaptation of large language models (LLMs) to new information or corrections without requiring full retraining. However, prior methods typica…
Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding
Keqin Peng, Liang Ding, Yuanxin Ouyang +3
Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights…
Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
Shaopeng Fu, Liang Ding, Jingfeng Zhang +1
Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to per…
TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
Yan Sun, Tiansheng Huang, Liang Ding +2
Zeroth-order optimization (ZO) has demonstrated remarkable promise in efficient fine-tuning tasks for Large Language Models (LLMs). In particular, recent advances incorporate the l…
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
Yuchun Miao, Sen Zhang, Liang Ding +3
This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking. Specifically, energy loss in the final la…
Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models
Shengsheng Zhou, Shuai Wang, Liang Ding +5
Large language models (LLMs) have shown strong performance in automated code generation, with few-shot prompting widely used for its simplicity and effectiveness. However, few-shot…