Saved in:
Bibliographic Details
Main Authors: Yin, Zhenyun, Wang, Shujie, Wang, Xuhong, Ma, Xingjun, Wang, Yinchun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16727
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915941086920704
author Yin, Zhenyun
Wang, Shujie
Wang, Xuhong
Ma, Xingjun
Wang, Yinchun
author_facet Yin, Zhenyun
Wang, Shujie
Wang, Xuhong
Ma, Xingjun
Wang, Yinchun
contents Improving the reliability of large language models (LLMs) is critical for deploying them in real-world scenarios. In this paper, we propose \textbf{Deliberative Searcher}, the first framework to integrate certainty calibration with retrieval-based search for open-domain question answering. The agent performs multi-step reflection and verification over Wikipedia data and is trained with a reinforcement learning algorithm that optimizes for accuracy under a soft reliability constraint. Empirical results show that proposed method improves alignment between model confidence and correctness, leading to more trustworthy outputs. This paper will be continuously updated.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
Yin, Zhenyun
Wang, Shujie
Wang, Xuhong
Ma, Xingjun
Wang, Yinchun
Artificial Intelligence
Improving the reliability of large language models (LLMs) is critical for deploying them in real-world scenarios. In this paper, we propose \textbf{Deliberative Searcher}, the first framework to integrate certainty calibration with retrieval-based search for open-domain question answering. The agent performs multi-step reflection and verification over Wikipedia data and is trained with a reinforcement learning algorithm that optimizes for accuracy under a soft reliability constraint. Empirical results show that proposed method improves alignment between model confidence and correctness, leading to more trustworthy outputs. This paper will be continuously updated.
title Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
topic Artificial Intelligence
url https://arxiv.org/abs/2507.16727