mlsanityData to 7 Oct 2026

Unsupervised Commonsense Question Answering with Self-Talk

arXiv 2004.05483 ↗First posted 11 Apr 2020cs.CLcited by 161

Not on the map. Why?

Cited by 48 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implicit source of world knowledge, or resort to external knowledge bases (KBs) to incorporate additional relevant knowledge. We propose an unsupervised framework based on self-talk as a novel alternative to multiple-choice commonsense tasks. Inspired by inquiry-based discovery learning (Bruner, 1961), our approach inquires language models with a number of information seeking questions such as "textitwhat is the definition of ..." to discover additional background knowledge. Empirical results demonstrate that the self-talk procedure substantially improves the performance of zero-shot language model baselines on four out of six commonsense benchmarks, and competes with models that obtain knowledge from external KBs. While our approach improves performance on several benchmarks, the self-talk induced knowledge even when leading to correct answers is not always seen as useful by human judges, raising interesting questions about the inner-workings of pre-trained language models for commonsense reasoning.

Key facts. Cited by 161 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 51; 2023: 46; 2024: 18; 2025: 9; 2026: 1.

161 papers.

Sort:

By area:

  1. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  2. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  3. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  4. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  5. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  6. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  7. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 292
  8. 2022Generating Sequences by Learning to Self-Correctcited by 271
  9. 2022Can language models learn from explanations in context?cited by 248
  10. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  11. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  12. 2023Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Modelscited by 161
38 more
  1. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  2. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
  3. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  4. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tangocited by 128
  5. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  6. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  7. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  8. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  9. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  10. 2022Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generatorcited by 68
  11. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
  12. 2022Recitation-Augmented Language Modelscited by 65
  13. 2023ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Modelscited by 63
  14. 2022Parsel: Algorithmic Reasoning with Language Models by Composing Decompositionscited by 62
  15. 2024NExT: Teaching Large Language Models to Reason about Code Executioncited by 60
  16. 2022minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Modelscited by 58
  17. 2021BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Beliefcited by 56
  18. 2021A Systematic Investigation of Commonsense Knowledge in Large Language Modelscited by 56
  19. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  20. 2023Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Modelscited by 46
  21. 2023Training Chain-of-Thought via Latent-Variable Inferencecited by 46
  22. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  23. 2021Grounding 'Grounding' in NLPcited by 44
  24. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  25. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 42
  26. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agentscited by 41
  27. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  28. 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
  29. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  30. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  31. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  32. 2021Relational World Knowledge Representation in Contextual Language Models: A Reviewcited by 31
  33. 2021Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resourcescited by 30
  34. 2021Dimensions of Commonsense Knowledgecited by 29
  35. 2021Flexible Generation of Natural Language Deductionscited by 28
  36. 2024Steering Language Models with Game-Theoretic Solverscited by 28
  37. 2025Entropy-based Exploration Conduction for Multi-step Reasoningcited by 28
  38. 2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26

50 most cited of 161 All 161 (JSON)