13 papers · 1 filter
Verifying Chain-of-Thought Reasoning via Its Computational Graph
Zheng Zhao, Yeskendir Koishekenov, Xianjun Yang +2
Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a compu…
Your thoughts tell who you are: Characterize the reasoning patterns of LRMs
Yida Chen, Yuning Mao, Xianjun Yang +7
Current comparisons of large reasoning models (LRMs) focus on macro-level statistics such as task accuracy or reasoning length. Whether different LRMs reason differently remains an…
Many-Turn Jailbreaking
Xianjun Yang, Liqiang Xiao, Shiyang Li +5
Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one speci…
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang +4
Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…
Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
Xianjun Yang, Shaoliang Nie, Lijuan Liu +5
Instruction tuning data are often quantity-saturated due to the large volume of data collection and fast model iteration, leaving data selection important but underexplored. Existi…
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding
Zekun Li, Xianjun Yang, Kyuri Choi +11
Scientific figure interpretation is a crucial capability for AI-driven scientific assistants built on advanced Large Vision Language Models. However, current datasets and benchmark…