2 citations · 2 across the 9 of their papers we have counts for
9 papers
Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
Jiachen Yu, Zhihao Xu, Junjie Wang +1
Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for reinforcement learning. Howeve…
AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
Jianhao Ruan, Zhihao Xu, Yiran Peng +9
Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools parad…
Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text
Zhihao Xu, Rumei Li, Jiahuan Li +4
Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and re…
Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models
Shuang Liang, Zhihao Xu, Jialing Tao +2
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection m…
Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models
Shuang Liang, Zhihao Xu, Jiaqi Weng +3
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential,…
Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
Haoran Jin, Meng Li, Xiting Wang +4
Aligning Large Language Models (LLMs) with human values has attracted increasing attention since it provides clarity, transparency, and the ability to adapt to evolving scenarios.…
REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
Zhihao Xu, Yongqi Tong, Xin Zhang +2
Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises oth…
Evaluating Readability and Faithfulness of Concept-based Explanations
Meng Li, Haoran Jin, Ruixuan Huang +5
With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a pro…
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Zhihao Xu, Ruixuan Huang, Changyu Chen +1
Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Conce…