Skip to main content

Spring Deadline: Sunday, March 1 @ 11:59pm PT. Click here to apply.

Back to Research
Accepted to NAACL SRW 2025

CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning

Andrew Rufail, Daniel Kim

Abstract

CLEAR is 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. Similar to how humans would contrast and incorporate multiple feedback they receive to form a high-quality evaluation, CLEAR contrasts expert and amateur model feedback. The method demonstrates notable improvements across multiple domains: up to 19.6% relative increase in story outline interestingness, up to 18.5% increase in constrained generation coverage, up to 6.7% improvement in mathematical reasoning accuracy, and a decrease of up to 22% in toxicity.

Citation

Andrew Rufail, Daniel Kim. "CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning". Accepted to NAACL SRW 2025.

Details

Conference
Accepted to NAACL SRW 2025
Authors
2 authors

Publish Your Research

Join Algoverse and work with world-class mentors to publish at top AI conferences.

Start Your Application