CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917981786734592 |
|---|---|
| author | Rufail, Andrew Kim, Daniel O'Brien, Sean Zhu, Kevin |
| author_facet | Rufail, Andrew Kim, Daniel O'Brien, Sean Zhu, Kevin |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07116 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning Rufail, Andrew Kim, Daniel O'Brien, Sean Zhu, Kevin Computation and Language 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). |
| title | CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.07116 |