# Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting

arXiv: https://arxiv.org/abs/2302.04813 · HTML: https://mlsanity.com/paper/2302.04813/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 9 Feb 2023.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 14 of 14)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Demystifying Prompts in Language Models via Perplexity Estimation](https://mlsanity.com/paper/2212.04037/) (2022)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango](https://mlsanity.com/paper/2209.07686/) (2022)
- [Explanations from Large Language Models Make Small Reasoners Better](https://mlsanity.com/paper/2210.06726/) (2022)
- [TEMPERA: Test-Time Prompting via Reinforcement Learning](https://mlsanity.com/paper/2211.11890/) (2022)

## Built on by (most cited first, 12 of 12)

- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [SatLM: Satisfiability-Aided Language Models Using Declarative Prompting](https://mlsanity.com/paper/2305.09656/) (2023)
- [Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models](https://mlsanity.com/paper/2403.12388/) (2024)
- [EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning](https://mlsanity.com/paper/2309.10687/) (2023)
- [Monotonic Paraphrasing Improves Generalization of Language Model Prompting](https://mlsanity.com/paper/2403.16038/) (2024)
- [Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning](https://mlsanity.com/paper/2311.07099/) (2023)
- [Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models](https://mlsanity.com/paper/2410.21728/) (2024)
- [A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models](https://mlsanity.com/paper/2310.18358/) (2023)
- [Has My System Prompt Been Used? Large Language Model Prompt Membership Inference](https://mlsanity.com/paper/2502.09974/) (2025)
- [Considering Length Diversity in Retrieval-Augmented Summarization](https://mlsanity.com/paper/2503.09249/) (2025)
- [Psychology-Driven Enhancement of Humour Translation](https://mlsanity.com/paper/2507.09259/) (2025)

## Abstract (arXiv)

Recent work has shown how to prompt large language models with explanations to obtain strong performance on textual reasoning tasks, i.e., the chain-of-thought paradigm. However, subtly different explanations can yield widely varying downstream task accuracy. Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion. We first generate sets of candidate explanations for each example in the prompt using a leave-one-out scheme, then find an effective combination of these explanations with a two-stage framework. We first evaluate explanations for each in-context example in isolation according to two proxy metrics, log likelihood and accuracy on new examples. Then, we search over combinations of explanations to find one that yields high performance against a silver-labeled development set. Across four textual reasoning tasks spanning question answering, mathematical reasoning, and natural language inference, results show that our proxy metrics correlate with ground truth accuracy and our overall method can effectively improve prompts over crowdworker annotations and naive search strategies