Prompt Engineering and Calibration for Zero-Shot Commonsense Reasoning
On the map: LLM reasoning → Prompting and chain-of-thought reasoning
Abstract (arXiv)
Prompt engineering and calibration make large language models excel at reasoning tasks, including multiple choice commonsense reasoning. From a practical perspective, we investigate and evaluate these strategies on smaller language models. Through experiments on five commonsense reasoning benchmarks, we find that each strategy favors certain models, but their joint effects are mostly negative.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 0 of its 24 references that are in the map. First posted on arXiv 14 Apr 2023.
Builds on
0 of 24 references.
No references here yet.
Built on by
Citing papers per year: 2024: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Large Language Models are Contrastive Reasoners
- 2025Zero-Shot Commonsense Validation and Reasoning with Large Language Models: An Evaluation on SemEval-2020 Task 4 Dataset
- 2023Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis
- 2026Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
- 2025Who Benchmarks the Benchmarks? Towards Comprehensive Evaluation of Commonsense Reasoning Benchmarks
- 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?
- 2025Zero-Shot Verification-guided Chain of Thoughts