# Large Language Models Are Also Good Prototypical Commonsense Reasoners

arXiv: https://arxiv.org/abs/2309.13165 · HTML: https://mlsanity.com/paper/2309.13165/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [A Survey of Knowledge-Enhanced Text Generation](https://mlsanity.com/paper/2010.04389/) (2020)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [CommonsenseQA 2.0: Exposing the Limits of AI through Gamification](https://mlsanity.com/paper/2201.05320/) (2022)
- [KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning](https://mlsanity.com/paper/2009.12677/) (2020)
- [Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context](https://mlsanity.com/paper/1911.10484/) (2019)
- [ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning](https://mlsanity.com/paper/2005.00771/) (2020)
- [How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models](https://mlsanity.com/paper/2209.01390/) (2022)
- [Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2201.12438/) (2022)
- [Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources](https://mlsanity.com/paper/2011.02705/) (2020)
- [I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning](https://mlsanity.com/paper/2011.00766/) (2020)
- [KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering](https://mlsanity.com/paper/2305.08347/) (2023)

## Built on by (most cited first, 1 of 1)

- [Large Language Model-assisted Autonomous Vehicle Recovery from Immobilization](https://mlsanity.com/paper/2510.26023/) (2025)

## Abstract (arXiv)

Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence. Traditional fine-tuning approaches can be resource-intensive and potentially compromise a model's generalization capacity. Furthermore, state-of-the-art language models like GPT-3.5 and Claude are primarily accessible through API calls, which makes fine-tuning models challenging. To address these challenges, we draw inspiration from the outputs of large models for tailored tasks and semi-automatically developed a set of novel prompts from several perspectives, including task-relevance, supportive evidence generation (e.g. chain-of-thought and knowledge), diverse path decoding to aid the model. Experimental results on ProtoQA dataset demonstrate that with better designed prompts we can achieve the new state-of-art(SOTA) on the ProtoQA leaderboard, improving the Max Answer@1 score by 8%, Max Incorrect@1 score by 4% (breakthrough 50% for the first time) compared to the previous SOTA model and achieved an improvement on StrategyQA and CommonsenseQA2.0 (3% and 1%, respectively). Furthermore, with the generated Chain-of-Thought and knowledge, we can improve the interpretability of the model while also surpassing the previous SOTA models. We hope that our work can provide insight for the NLP community to develop better prompts and explore the potential of large language models for more complex reasoning tasks.