arXiv AI By Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Jingxiang Chen, Mohammad Kachuee, Teja Gollapudi, Yiwei Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Read the original on arXiv AI →

arXiv:2509. 25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 14

To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning

arXiv:2607. 10738v1 Announce Type: cross Abstract: Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks.

By Fengji Zhang, Tianyu Fan, Yuxiang Zheng, Xinyao Niu, Chengen Huang, Jacky Keung, Bei Chen
Hugging Face Trending Papers
Jul 12

To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning

Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks. However, we argue that current training paradigms harbor a critical vulnerability: they predominantly reward correct answers but fail to penalize fabricated ones when retrieval fails, thereby implicitly exacerbating hallucinations.