6 papers
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…
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…
MedGEN-Bench: Contextually entangled benchmark for open-ended multimodal medical generation
Junjie Yang, Yuhao Yan, Gang Wu +8
As Vision-Language Models (VLMs) increasingly gain traction in medical applications, clinicians are progressively expecting AI systems not only to generate textual diagnoses but al…
Retrieval-Augmented Generation with Hierarchical Knowledge
Haoyu Huang, Yongfeng Huang, Junjie Yang +5
Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks. However, existing RAG…
Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis
Pengfei Wang, Guohai Xu, Weinong Wang +3
Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate…
Think When You Need: Self-Adaptive Chain-of-Thought Learning
Junjie Yang, Ke Lin, Xing Yu
Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches direct…