5 papers
Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
Zheyuan Zhang, Manqing Mao, Hong Wang +8
Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of ro…
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
Taiwei Shi, Zhuoer Wang, Longqi Yang +12
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on hum…
WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
Yuqing Zhou, Zhuoer Wang, Jie Yuan +4
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substant…
DHP Benchmark: Are LLMs Good NLG Evaluators?
Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang +7
Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks; this is often referred to as ``LLM-as-a-judge'' paradigm. However, t…
FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking
Zhuoer Wang, Leonardo F. R. Ribeiro, Alexandros Papangelis +6
API call generation is the cornerstone of large language models' tool-using ability that provides access to the larger world. However, existing supervised and in-context learning a…