mlsanityData to 14 Oct 2026

MuTual: A Dataset for Multi-Turn Dialogue Reasoning

arXiv 2004.04494 ↗First posted 9 Apr 2020cs.CLcited by 115

Not on the map. Why?

Abstract (arXiv)

Non-task oriented dialogue systems have achieved great success in recent years due to largely accessible conversation data and the development of deep learning techniques. Given a context, current systems are able to yield a relevant and fluent response, but sometimes make logical mistakes because of weak reasoning capabilities. To facilitate the conversation reasoning research, we introduce MuTual, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams. Compared to previous benchmarks for non-task oriented dialogue systems, MuTual is much more challenging since it requires a model that can handle various reasoning problems. Empirical results show that state-of-the-art methods only reach 71%, which is far behind the human performance of 94%, indicating that there is ample room for improving reasoning ability. MuTual is available at https://github.com/Nealcly/MuTual.

Key facts. Cited by 115 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 30; 2023: 25; 2024: 21; 2025: 7; 2026: 12.

115 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  3. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  4. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  5. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 183
  6. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  7. 2023AutoMix: Automatically Mixing Language Modelscited by 125
  8. 2024WavLLM: Towards Robust and Adaptive Speech Large Language Modelcited by 109
  9. 2024Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescuecited by 103
  10. 2023The Generative AI Paradox: "What It Can Create, It May Not Understand"cited by 98
  11. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 83
  12. 2024Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inferencecited by 75
38 more
  1. 2021Comparing Test Sets with Item Response Theorycited by 57
  2. 2024Self-evolving Agents with reflective and memory-augmented abilitiescited by 52
  3. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41
  4. 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
  5. 2022CICERO: A Dataset for Contextualized Commonsense Inference in Dialoguescited by 38
  6. 2023CBQ: Cross-Block Quantization for Large Language Modelscited by 34
  7. 2021Commonsense-Focused Dialogues for Response Generation: An Empirical Studycited by 30
  8. 2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26
  9. 2022RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoningcited by 22
  10. 2022Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Qualitycited by 22
  11. 2021Structural Pre-training for Dialogue Comprehensioncited by 20
  12. 2021CIDER: Commonsense Inference for Dialogue Explanation and Reasoningcited by 20
  13. 2023Robust Prompt Optimization for Large Language Models Against Distribution Shiftscited by 19
  14. 2025MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoningcited by 16
  15. 2024Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcomcited by 15
  16. 2021Probing Commonsense Explanation in Dialogue Response Generationcited by 13
  17. 2021Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehensioncited by 13
  18. 2021Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehensioncited by 13
  19. 2022Towards Fine-grained Causal Reasoning and QAcited by 13
  20. 2023GLoRE: Evaluating Logical Reasoning of Large Language Modelscited by 13
  21. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  22. 2022Knowledge Infused Decodingcited by 12
  23. 2022LogiGAN: Learning Logical Reasoning via Adversarial Pre-trainingcited by 11
  24. 2022Multiview Contextual Commonsense Inference: A New Dataset and Taskcited by 11
  25. 2022ComFact: A Benchmark for Linking Contextual Commonsense Knowledgecited by 11
  26. 2024Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolboxcited by 11
  27. 2021Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledgecited by 10
  28. 2024Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passescited by 10
  29. 2025DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editingcited by 10
  30. 2024MEMoE: Enhancing Model Editing with Mixture of Experts Adaptorscited by 9
  31. 2024ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRAcited by 8
  32. 2022Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modelingcited by 7
  33. 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Artcited by 7
  34. 2023Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarizationcited by 7
  35. 2024MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systemscited by 7
  36. 2021Smoothing Dialogue States for Open Conversational Machine Readingcited by 6
  37. 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarizationcited by 6
  38. 2023SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedbackcited by 6

50 most cited of 115 All 115 (JSON)