mlsanityData to 7 Oct 2026

MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

arXiv 2109.12595 ↗First posted 26 Sep 2021cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single given document or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such a task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based context in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 26 Sep 2021.

Builds on

26 of 35 references.

References · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  8. 2018CoQA: A Conversational Question Answering Challengecited by 674
  9. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  10. 2018QuAC : Question Answering in Contextcited by 379
  11. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  12. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
14 more
  1. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  2. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  3. 2020Open-Retrieval Conversational Question Answeringcited by 99
  4. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  5. 2018Interpretation of Natural Language Rules in Conversational Machine Readingcited by 72
  6. 2020Relevance-guided Supervision for OpenQA with ColBERTcited by 71
  7. 2021Few-Shot Conversational Dense Retrievalcited by 71
  8. 2020DoQA -- Accessing Domain-Specific FAQs via Conversational QAcited by 42
  9. 2020Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Readingcited by 33
  10. 2021Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Taskscited by 32
  11. 2021Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoringcited by 29
  12. 2020Topic Propagation in Conversational Searchcited by 10
  13. 2021A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answeringcited by 7
  14. 2021Weakly-Supervised Open-Retrieval Conversational Question Answeringcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 18; 2024: 15; 2025: 7; 2026: 10.

53 papers.

Sort:

By area:

  1. 2023L-Eval: Instituting Standardized Evaluation for Long Context Language Modelscited by 232
  2. 2024A Survey on Large Language Model Acceleration based on KV Cache Managementcited by 125
  3. 2023Prompted LLMs as Chatbot Modules for Long Open-domain Conversationcited by 61
  4. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systemscited by 50
  5. 2022INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactionscited by 27
  6. 2024Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLPcited by 27
  7. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
  8. 2024A Survey of Conversational Searchcited by 22
  9. 2024RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialoguescited by 19
  10. 2023Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogscited by 11
  11. 2023Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generationcited by 11
  12. 2023SuperDialseg: A Large-scale Dataset for Supervised Dialogue Segmentationcited by 10
38 more
  1. 2023Diversify Question Generation with Retrieval-Augmented Style Transfercited by 10
  2. 2023textitDial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuningcited by 9
  3. 2024Self-Refinement of Language Models from External Proxy Metrics Feedbackcited by 9
  4. 2025WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generationcited by 9
  5. 2024Multi-Document Grounded Multi-Turn Synthetic Dialog Generationcited by 7
  6. 2025Granite Embedding R2 Modelscited by 7
  7. 2023Coarse-to-Fine Knowledge Selection for Document Grounded Dialogscited by 6
  8. 2023The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intentscited by 6
  9. 2023"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledgecited by 6
  10. 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inferencecited by 6
  11. 2023Zebra: Extending Context Window with Layerwise Grouped Local-Global Attentioncited by 6
  12. 2024Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Modelscited by 6
  13. 2023Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialoguescited by 5
  14. 2024INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Modelscited by 5
  15. 2022CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversationscited by 4
  16. 2023Causal Document-Grounded Dialogue Pre-trainingcited by 4
  17. 2024Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rightscited by 4
  18. 2024Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Taskscited by 3
  19. 2024From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialoguescited by 3
  20. 2022Human in the loop approaches in multi-modal conversational task guidance system developmentcited by 2
  21. 2025KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialoguescited by 2
  22. 2026M3Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactionscited by 2
  23. 2023Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Readingcited by 1
  24. 2024R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Modelscited by 1
  25. 2024Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Modelscited by 1
  26. 2025RAGAPHENE: A RAG Annotation Platform with Human Enhancements and Editscited by 1
  27. 2026ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answeringcited by 1
  28. 2023Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languagescited by 0
  29. 2023How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Contextcited by 0
  30. 2023Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generationcited by 0
  31. 2024Structured List-Grounded Question Answeringcited by 0
  32. 2025Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questionscited by 0
  33. 2025A Longitudinal Study on Different Annotator Feedback Loops in Complex RAG Taskscited by 0
  34. 2026Orcheo: A Modular Full-Stack Platform for Conversational Searchcited by 0
  35. 2026Structures Facilitate Retrieve, Rerank, and Generatecited by 0
  36. 2026AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agentscited by 0
  37. 2026CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAGcited by 0
  38. 2026TRACE: Trustworthy Retrieval-Augmented Conversational Enginecited by 0

50 most cited of 53 All 53 (JSON)