9 papers
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
Yanjiang Liu, Jie Lou, Xinyan Guan +7
On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identif…
Coupled Variational Reinforcement Learning for Language Model General Reasoning
Xueru Wen, Jie Lou, Yanjiang Liu +6
While reinforcement learning has achieved impressive progress in language model reasoning, it is constrained by the requirement for verifiable rewards. Recent verifier-free RL meth…
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
Xueru Wen, Jie Lou, Xinyu Lu +5
As AI capabilities increasingly surpass human proficiency in complex tasks, current alignment techniques, including SFT and RLHF, face fundamental challenges in ensuring reliable o…
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
Qianhao Yuan, Qingyu Zhang, Yanjiang Liu +6
Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-w…
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…
Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction
Tianyun Zhong, Guozhao Mo, Yanjiang Liu +9
With the emergence of large language models (LLMs), there is an expectation that LLMs can effectively extract explicit information from complex real-world documents (e.g., papers,…