7 papers
Reasoning Compression with Mixed-Policy Distillation
Han Yang, Mingyan Wu, Bailan He +4
Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive token usage and high inferenc…
Deep Research Brings Deeper Harm
Shuo Chen, Zonggen Li, Zhen Han +7
Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detai…
Bag of Tricks for Subverting Reasoning-based Safety Guardrails
Shuo Chen, Zhen Han, Haokun Chen +6
Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs'…
Supposedly Equivalent Facts That Aren't? Entity Frequency in Pre-training Induces Asymmetry in LLMs
Yuan He, Bailan He, Zifeng Ding +8
Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "w…
Distilling Tool Knowledge into Language Models via Back-Translated Traces
Xingyue Huang, Xianglong Hu, Zifeng Ding +9
Large language models (LLMs) often struggle with mathematical problems that require exact computation or multi-step algebraic reasoning. Tool-integrated reasoning (TIR) offers a pr…
Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
Shuo Chen, Zhen Han, Bailan He +5
Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the t…