mlsanityData to 7 Oct 2026

Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models

arXiv 2309.12940 ↗First posted 22 Sep 2023cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts. In this study, we propose a novel "Self-Explanation" prompting strategy to enhance the comprehension abilities of LLMs in multi-turn dialogues. This task-agnostic approach requires the model to analyze each dialogue utterance before task execution, thereby improving performance across various dialogue-centric tasks. Experimental results from six benchmark datasets confirm that our method consistently outperforms other zero-shot prompts and matches or exceeds the efficacy of few-shot prompts, demonstrating its potential as a powerful tool in enhancing LLMs' comprehension in complex dialogue tasks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 41 of its 50 references that are in the map. First posted on arXiv 22 Sep 2023.

Builds on

41 of 50 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  9. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  11. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  12. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
29 more
  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  2. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  3. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  4. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  5. 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 636
  6. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  7. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 426
  8. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  9. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  10. 2023MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learningcited by 171
  11. 2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 114
  12. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  13. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  14. 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labelscited by 88
  15. 2023SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agentscited by 71
  16. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  17. 2020STAR: A Schema-Guided Dialog Dataset for Transfer Learningcited by 43
  18. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  19. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  20. 2022Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systemscited by 28
  21. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  22. 2022Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speechcited by 25
  23. 2023UniSA: Unified Generative Framework for Sentiment Analysiscited by 17
  24. 2023Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignmentcited by 13
  25. 2023Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representationcited by 11
  26. 2022AnyTOD: A Programmable Task-Oriented Dialog Systemcited by 10
  27. 2023Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewritingcited by 9
  28. 2023Empathetic Response Generation via Emotion Cause Transition Graphcited by 8
  29. 2023UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Promptcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  2. 2024Large Language Models Meet NLP: A Surveycited by 102
  3. 2025ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMscited by 8
  4. 2024An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guidecited by 7
  5. 2025Counterfactual Simulatability of LLM Explanations for Generation Taskscited by 7