11 papers
Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
Zesheng Shi, Xue Li, Chenrui Dai +1
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model m…
A Heuristic Perspective on Debiasing Language Models
Tian Lan, Yemin Wang, Chuancheng Shi +6
Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing methods often rely on counter…
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
Weiyang Guo, Zesheng Shi, Longhui Zhang +3
Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajector…
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
Zhuo Li, Guodong Du, Zesheng Shi +5
Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities with strict memory and inferen…
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
Wu Li, Yigeng Zhou, Zesheng Shi +3
While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality…
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
Weiyang Guo, Zesheng Shi, Liye Zhao +5
While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face significant limitations: Zero-RL suf…
MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
Hongjie Zheng, Zesheng Shi, Ping Yi
Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with in…
Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
Weiyang Guo, Zesheng Shi, Zhuo Li +6
As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect…
Safety Alignment via Constrained Knowledge Unlearning
Zesheng Shi, Yucheng Zhou, Jing Li
Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful k…
Knowledge Fusion of Large Language Models Via Modular SkillPacks
Guodong Du, Zhuo Li, Xuanning Zhou +9
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent…
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
Feng Wang, Zesheng Shi, Bo Wang +2
We present ReaderLM-v2, a compact 1.5 billion parameter language model designed for efficient web content extraction. Our model processes documents up to 512K tokens, transforming…