paper-with-me

홈 › Papers

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

2026-07-12 · Fengji Zhang, Tianyu Fan, Yuxiang Zheng, Xinyao Niu, Chengen Huang, Jacky Keung, Bei Chen arxiv

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. To address this, we propose Abstention-Aware Reinforcement Learning (AWA-RL), which dynamically shapes the abstention reward utilizing the model's query-specific prior capabilities and continuous on-policy training observations. We also introduce a novel metric, RA-F1, to measure the capability-reliability trade-off. Compared to non-abstaining baselines, AWA-RL boosts absolute precision by up to 10.3% and overall RA-F1 by 2.9%, with only marginal sacrifice in raw accuracy. These results confirm that AWA-RL successfully yields highly capable and reliable search agents. The code, data, and model weights are publicly available at https://github.com/zfj1998/AWA-RL.

📄 PDF Abstract BibTeX arXiv:2607.10738

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward

2025-10-28 · Hao An, Yang Xu arxiv

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, th…

Reinforcement Learning

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning

2026-04-03 · Cheng Gao, Cheng Huang, Kangyang Luo, Ziqing Qiao 외 arxiv

Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations. While existing reinforcement learning methods foster autonomous abs…

Reinforcement Learning

Distinguishing Ignorance from Error in LLM Hallucinations

2024-10-29 · Adi Simhi, Jonathan Herzig, Idan Szpektor, Yonatan Belinkov

Large language models (LLMs) are susceptible to hallucinations-outputs that are ungrounded, factually incorrect, or inconsistent with prior generations. We focus on close-book Question Answering (CBQA), where previous wo…

HallucinationQuestion Answering

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

2026-06-27 · Han Luo, Bingbing Wen, Lucy Lu Wang arxiv

LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable in the available environment. In such c…

Question Answering

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations

2024-04-16 · Christian Tomani, Kamalika Chaudhuri, Ivan Evtimov, Daniel Cremers 외

A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable …

Question Answering