11 papers
FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language Models
Jiayuan Ma, Yuqi Lu, Weiyang Guo +5
Vision-language models (VLMs) are increasingly deployed in multi-turn settings where users may describe visual content with incorrect assumptions. Yet existing evaluations rarely i…
Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time
Zeen Zhu, Zhuo Li, Weiyang Guo +4
A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatc…
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…
Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
Weiyang Guo, Zesheng Shi, Zeen Zhu +3
Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical task…
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…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
Ning Liao, Xiaoxing Wang, Zehao Lin +18
A large language model (LLM) with knowledge in both scientific and general tasks is the foundation of science general intelligence. However, directly continued pretraining an LLM u…
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…
Multi-objective Large Language Model Alignment with Hierarchical Experts
Zhuo Li, Guodong Du, Weiyang Guo +8
Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of hu…
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
Weiyang Guo, Jing Li, Wenya Wang +4
The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intention…