mlsanityData to 7 Oct 2026

Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check

arXiv 2403.18243 ↗First posted 27 Mar 2024cs.AIcited by 24

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) aims to generate more reliable and accurate responses, by augmenting large language models (LLMs) with the external vast and dynamic knowledge. Most previous work focuses on using RAG for single-round question answering, while how to adapt RAG to the complex conversational setting wherein the question is interdependent on the preceding context is not well studied. In this paper, we propose a conversation-level RAG approach, which incorporates fine-grained retrieval augmentation and self-check for conversational question answering (CQA). In particular, our approach consists of three components, namely conversational question refiner, fine-grained retriever and self-check based response generator, which work collaboratively for question understanding and relevant information acquisition in conversational settings. Extensive experiments demonstrate the great advantages of our approach over the state-of-the-art baselines. Moreover, we also release a Chinese CQA dataset with new features including reformulated question, extracted keyword, retrieved paragraphs and their helpfulness, which facilitates further researches in RAG enhanced CQA.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 40 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

25 of 40 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  9. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  10. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  11. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  12. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
13 more
  1. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  2. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  3. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  4. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 147
  5. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  6. 2023Hallucinations in Large Multilingual Translation Modelscited by 126
  7. 2023WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferencescited by 100
  8. 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 95
  9. 2020Question Rewriting for Conversational Question Answeringcited by 93
  10. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  11. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  12. 2022On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Methodcited by 12
  13. 2023S2M: Converting Single-Turn to Multi-Turn Datasets for Conversational Question Answeringcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 13; 2026: 6.

24 papers.

Sort:

By area:

  1. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  2. 2024Adaptive Retrieval-Augmented Generation for Conversational Systemscited by 22
  3. 2024A Survey of Conversational Searchcited by 22
  4. 2025UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversationscited by 11
  5. 2024MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Modelscited by 9
  6. 2025WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generationcited by 9
  7. 2024CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generationcited by 8
  8. 2025Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detectioncited by 8
  9. 2025DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generationcited by 7
  10. 2025Automatic Dataset Generation for Knowledge Intensive Question Answering Taskscited by 6
  11. 2025Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answeringcited by 6
  12. 2024A Multi-Source Retrieval Question Answering Framework Based on RAGcited by 4
12 more
  1. 2025Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech Synthesiscited by 4
  2. 2025Unlocking Speech Instruction Data Potential with Query Rewritingcited by 4
  3. 2026VikingMem: A Memory Base Management System for Stateful LLM-based Applicationscited by 2
  4. 2025CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context Semanticscited by 1
  5. 2025A Survey of the State-of-the-Art in Conversational Question Answering Systemscited by 1
  6. 2025Causal Retrieval with Semantic Considerationcited by 0
  7. 2025M-Eval: A Heterogeneity-Based Framework for Multi-evidence Validation in Medical RAG Systemscited by 0
  8. 2026Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QAcited by 0
  9. 2026AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversationscited by 0
  10. 2026MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Banditscited by 0
  11. 2026Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agentscited by 0
  12. 2026S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  2. 2026Augmenting Question Answering with A Hybrid RAG Approach
  3. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
  4. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
  5. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
  6. 2025Multiple Abstraction Level Retrieve Augment Generation
  7. 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
  8. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration