# Unsupervised Commonsense Question Answering with Self-Talk

arXiv: https://arxiv.org/abs/2004.05483 · HTML: https://mlsanity.com/paper/2004.05483/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2020.

## Built on by (most cited first, 30 of 161)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango](https://mlsanity.com/paper/2209.07686/) (2022)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [Iteratively Prompt Pre-trained Language Models for Chain of Thought](https://mlsanity.com/paper/2203.08383/) (2022)
- [Unleashing the potential of prompt engineering for large language models](https://mlsanity.com/paper/2310.14735/) (2023)
- [Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator](https://mlsanity.com/paper/2206.08082/) (2022)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [Recitation-Augmented Language Models](https://mlsanity.com/paper/2210.01296/) (2022)
- [Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions](https://mlsanity.com/paper/2212.10561/) (2022)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://mlsanity.com/paper/2303.16421/) (2023)
- [NExT: Teaching Large Language Models to Reason about Code Execution](https://mlsanity.com/paper/2404.14662/) (2024)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [A Systematic Investigation of Commonsense Knowledge in Large Language Models](https://mlsanity.com/paper/2111.00607/) (2021)

## 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.