3 citations · 12 across the 14 of their papers we have counts for
15 papers
Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
Yiming Wang, Yikang Liu, Qingyuan Tian +4
Self-rewarding reinforcement learning (RL) enables large language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods construct reward references fro…
LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation
Xingyu Chen, Rui Wang, Zhaopeng Tu +1
Fixed benchmarks are costly to renew and cannot adapt their questions to model-specific failures. We ask whether LLMs can instead discover one another's weaknesses and turn those o…
The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
Xinbei Ma, Ruotian Ma, Xingyu Chen +14
LLM-based multi-agent systems demonstrate great potential for tackling complex problems, but how competition shapes their behavior remains underexplored. This paper investigates th…
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He +10
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Zhiwei He, Tian Liang, Jiahao Xu +12
Reinforcement learning (RL) with large language models shows promise in complex reasoning. However, its progress is hindered by the lack of large-scale training data that is suffic…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Yansi Li, Jiahao Xu, Tian Liang +8
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Tradi…
RaSA: Rank-Sharing Low-Rank Adaptation
Zhiwei He, Zhaopeng Tu, Xing Wang +7
Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stem…
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Yue Wang, Qiuzhi Liu, Jiahao Xu +11
Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks by scaling test-time compute and exhibiting human-like deep think…
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Xingyu Chen, Jiahao Xu, Tian Liang +11
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended c…
Evaluating Knowledge-based Cross-lingual Inconsistency in Large Language Models
Xiaolin Xing, Zhiwei He, Haoyu Xu +3
This paper investigates the cross-lingual inconsistencies observed in Large Language Models (LLMs), such as ChatGPT, Llama, and Baichuan, which have shown exceptional performance i…
Unsupervised Sign Language Translation and Generation
Zhengsheng Guo, Zhiwei He, Wenxiang Jiao +6
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns fro…
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
Tian Xia, Zhiwei He, Tong Ren +4
Bargaining is an important and unique part of negotiation between humans. As LLM-driven agents learn to negotiate and act like real humans, how to evaluate agents' bargaining abili…
Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Zhiwei He, Binglin Zhou, Hongkun Hao +5
Text watermarking technology aims to tag and identify content produced by large language models (LLMs) to prevent misuse. In this study, we introduce the concept of cross-lingual c…
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
Zhiwei He, Xing Wang, Wenxiang Jiao +4
Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation…
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
Tongxin Yuan, Zhiwei He, Lingzhong Dong +9
Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. Despite this, these LLM agents introduce unexpected saf…