Saved in:
Bibliographic Details
Main Authors: Qiu, Longpeng, Li, Ting, Mao, Shuai, Yang, Nan, Yan, Xiaohui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.03410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911250188861440
author Qiu, Longpeng
Li, Ting
Mao, Shuai
Yang, Nan
Yan, Xiaohui
author_facet Qiu, Longpeng
Li, Ting
Mao, Shuai
Yang, Nan
Yan, Xiaohui
contents Input errors in question-answering (QA) systems often lead to incorrect responses. Large language models (LLMs) struggle with this task, frequently failing to interpret user intent (misinterpretation) or unnecessarily altering the original question's structure (over-correction). We propose QuestionRAG, a framework that tackles these problems. To address misinterpretation, it enriches the input with external knowledge (e.g., search results, related entities). To prevent over-correction, it uses reinforcement learning (RL) to align the model's objective with precise correction, not just paraphrasing. Our results demonstrate that knowledge augmentation is critical for understanding faulty questions. Furthermore, RL-based alignment proves significantly more effective than traditional supervised fine-tuning (SFT), boosting the model's ability to follow instructions and generalize. By integrating these two strategies, QuestionRAG unlocks the full potential of LLMs for the question correction task.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge-Augmented Question Error Correction for Chinese Question Answer System with QuestionRAG
Qiu, Longpeng
Li, Ting
Mao, Shuai
Yang, Nan
Yan, Xiaohui
Computation and Language
Input errors in question-answering (QA) systems often lead to incorrect responses. Large language models (LLMs) struggle with this task, frequently failing to interpret user intent (misinterpretation) or unnecessarily altering the original question's structure (over-correction). We propose QuestionRAG, a framework that tackles these problems. To address misinterpretation, it enriches the input with external knowledge (e.g., search results, related entities). To prevent over-correction, it uses reinforcement learning (RL) to align the model's objective with precise correction, not just paraphrasing. Our results demonstrate that knowledge augmentation is critical for understanding faulty questions. Furthermore, RL-based alignment proves significantly more effective than traditional supervised fine-tuning (SFT), boosting the model's ability to follow instructions and generalize. By integrating these two strategies, QuestionRAG unlocks the full potential of LLMs for the question correction task.
title Knowledge-Augmented Question Error Correction for Chinese Question Answer System with QuestionRAG
topic Computation and Language
url https://arxiv.org/abs/2511.03410