Lune

EMNLP Findings2025

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction

Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, Dawei Yin

Abstract

In web search scenarios, erroneous queries frequently degrade users' experience through irrelevant results, underscoring the pivotal role of Chinese Spelling Check (CSC) systems. Although large language models (LLMs) exhibit remarkable capabilities across many tasks, they face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches, and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious overcorrection issues. To tackle this, we present RACQC, a Chinese Query Correction system with Retrieval-Augmented Generation(RAG) and multi-task learning. Specifically, our approach (1) integrates dynamic knowledge retrieval through entity-centric RAG to address rare entities and innovatively proposes an entity-title collaborative corpus, and (2) employs contrastive correction tasks to mitigate LLM over-correction tendencies. Furthermore, we propose MDCQC, a Multi-Domain Chinese Query Correction benchmark to test the model's entity correction capabilities. Extensive experiments on several datasets show that RACQC significantly outperforms existing baselines in CSC tasks. Specifically, RACQC achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset under the F 1 metric. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision cites ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning
  • Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum LearningJiawei Zhou, Hang Ding, Haiyun JiangACL 2026 · 4 citations
  2. Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise SupervisionGe Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang et al.ACL 2026 · 1 citation
  3. RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task EvaluationJiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo et al.ACL 2026

Builds on15

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  3. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  4. Spelling Error Correction with Soft-Masked BERTShaohua Zhang, Haoran Huang, Jicong Liu, Hang LiACL 2020 · 204 citations
  5. Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous SourcesXingxuan Li, Ruochen Zhao, Yew Ken Chia, Bosheng Ding et al.ICLR 2024 · 165 citations

Related papers

  1. ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMsChangchun Liu, Kai Zhang, Junzhe Jiang, Zirui Liu et al.EMNLP 2024 · 3 citations
  2. A Training-free LLM-based Approach to General Chinese Character Error CorrectionHouquan Zhou, Bo Zhang, Zhenghua Li, Ming Yan et al.ACL 2025
  3. Mixture of Small and Large Models for Chinese Spelling CheckZiheng Qiao, Houquan Zhou, Zhenghua LiACL 2025 · 4 citations
  4. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language ModelsHouquan Zhou, Zhenghua Li, Bo Zhang, Chen Li et al.EMNLP 2024 · 2 citations
  5. Benchmarking Retrieval-Augmented Generation in Multi-Modal ContextsZhenghao Liu, Xingsheng Zhu, Tianshuo Zhou, Xinyi Zhang et al.ACM MM 2025 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines