# CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning

arXiv: https://arxiv.org/abs/2504.07116 · HTML: https://mlsanity.com/paper/2504.07116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [Contrastive Decoding Improves Reasoning in Large Language Models](https://mlsanity.com/paper/2309.09117/) (2023)
- [Learning to Repair: Repairing model output errors after deployment using a dynamic memory of feedback](https://mlsanity.com/paper/2112.09737/) (2021)
- [NL-EDIT: Correcting semantic parse errors through natural language interaction](https://mlsanity.com/paper/2103.14540/) (2021)
- [PREADD: Prefix-Adaptive Decoding for Controlled Text Generation](https://mlsanity.com/paper/2307.03214/) (2023)
- [Decomposing Complex Queries for Tip-of-the-tongue Retrieval](https://mlsanity.com/paper/2305.15053/) (2023)
- [DOC: Improving Long Story Coherence With Detailed Outline Control](https://mlsanity.com/paper/2212.10077/) (2022)
- [THOUGHTSCULPT: Reasoning with Intermediate Revision and Search](https://mlsanity.com/paper/2404.05966/) (2024)
- [Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills](https://mlsanity.com/paper/2111.08596/) (2021)

## Abstract (arXiv)

We introduce CLEAR (Contrasting Textual Feedback with Experts and Amateurs for Reasoning), a novel approach to language model reasoning that leverages the strengths of a larger (expert) model and smaller (amateur) model. The expert and amateur models each provide feedback on a model's initial output and are contrasted with each other into refined feedback. This feedback is subsequently applied to iteratively improve CLEAR's responses. Our experiments demonstrate that CLEAR outperforms state-of-the-art methods in several challenging reasoning tasks, including story outline improvement (up to 19.6% relative increase in interestingness), constrained generation (up to 18.5% increase in coverage), mathematical reasoning (up to 6.7% improvement in accuracy) and mitigation of toxicity (decrease of up to 22% in toxicity).