ACL Findings2026
Structured Dialogue Refinement: Building Retrieval-Augmented Question Answering on Goal-Oriented Dialogues
Abstract
Retrieval-Augmented Generation (RAG) is widely used for question answering over wellstructured document corpora. However, a large amount of real-world problem-solving knowledge is captured in goal-oriented dialogues, where common ground misalignment between users and helpers gives rise to sparse, diffuse, and dynamically refined evidence that challenges standard RAG pipelines. We propose Structured Dialogue Refinement (SDR), a unified framework that adapts dialogue corpora for RAG at both the retrieval and generation stages without altering the underlying pipeline. Specifically, SDR introduces Dual Dialogue Querying for intent-aligned retrieval via issuecentric and solution-centric pseudo-documents, and Graph-Structured Dialogues coupled with a relevance-driven subgraph selection strategy to enable effective utilization of conversational evidence. We further adopt a nugget-based evaluation setup for dialogue-grounded RAG, enabling fine-grained analysis of retrieval coverage and grounded answer generation. Experiments demonstrate that SDR substantially improves both retrieval quality and grounded QA performance under dialogue-specific structural challenges.
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.
Lineage
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval Augmented Language Model Pre-Training
- The Power of Noise: Redefining Retrieval for RAG Systems cites Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- The Power of Noise: Redefining Retrieval for RAG Systems cites Retrieval Augmented Language Model Pre-Training
Builds on14
- Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
- 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
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga et al.NeurIPS 2024 · 395 citations
- Making Retrieval-Augmented Language Models Robust to Irrelevant ContextOri Yoran, Tomer Wolfson, Ori Ram, Jonathan BerantICLR 2024 · 361 citations
- The Power of Noise: Redefining Retrieval for RAG SystemsFlorin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice et al.SIGIR 2024 · 212 citations
Related papers
- CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMsYuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang et al.SIGIR 2025 · 9 citations
- SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge EnvironmentsXuanbo Fan, Tianqi Zhao, Yi Cheng, Chi Xiu et al.AAAI 2026
- MGRAG: Semantic Subgraph Matching and Graph-Aware Caching for Multimodal Retrieval-Augmented GenerationYubo Wang, Haoyang Li, Lei ChenVLDB 2026
- A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented GenerationNeal Lawton, Alfy Samuel, Anoop Kumar, Daben LiuEMNLP Findings 2025
- LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical RetrievalYaoze Zhang, Rong Wu, Pinlong Cai, Xiaoman Wang et al.AAAI 2026 · 7 citations
