7 papers
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Chengsong Huang, Wenhao Yu, Xiaoyang Wang +6
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, e…
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
Zhenwen Liang, Ruosen Li, Yujun Zhou +5
Assessing the quality of Large Language Model (LLM) outputs presents a critical challenge. Previous methods either rely on text-level information (e.g., reward models, majority vot…
Multimodal Reference Visual Grounding
Yangxiao Lu, Ruosen Li, Liqiang Jing +5
Visual grounding focuses on detecting objects from images based on language expressions. Recent Large Vision-Language Models (LVLMs) have significantly advanced visual grounding pe…
FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning
Ruosen Li, Ziming Luo, Xinya Du
Hallucinations in large language models (LLMs) pose significant challenges in tasks requiring complex multi-step reasoning, such as mathematical problem-solving. Existing approache…
AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
Ruosen Li, Ziming Luo, Quan Zhang +4
Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commen…
PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
Ruosen Li, Teerth Patel, Xinya Du
Nowadays, the quality of responses generated by different modern large language models (LLMs) is hard to evaluate and compare automatically. Recent studies suggest and predominantl…