Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914924798672896 |
|---|---|
| author | Shim, Jay Kruttschnitt, Grant Ma, Alyssa Kim, Daniel Chek, Benjamin Anand, Athul Zhu, Kevin O'Brien, Sean |
| author_facet | Shim, Jay Kruttschnitt, Grant Ma, Alyssa Kim, Daniel Chek, Benjamin Anand, Athul Zhu, Kevin O'Brien, Sean |
| contents | Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning. At the same time, models struggle with compositional generalization and are far from human performance on many reasoning-based benchmarks. Leveraging the success of chain-of-thought prompting, and also taking inspiration from context-aware decoding (CAD), we explore input-based contrasting methods to further encourage the type of reasoning induced by chain-of-thought prompting. While work remains to stabilize these results across datasets and models, the improvements we find warrant further investigation into input-based steering methods for context-aware reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03600 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models Shim, Jay Kruttschnitt, Grant Ma, Alyssa Kim, Daniel Chek, Benjamin Anand, Athul Zhu, Kevin O'Brien, Sean Computation and Language Rapidly increasing model scales coupled with steering methods such as chain-of-thought prompting have led to drastic improvements in language model reasoning. At the same time, models struggle with compositional generalization and are far from human performance on many reasoning-based benchmarks. Leveraging the success of chain-of-thought prompting, and also taking inspiration from context-aware decoding (CAD), we explore input-based contrasting methods to further encourage the type of reasoning induced by chain-of-thought prompting. While work remains to stabilize these results across datasets and models, the improvements we find warrant further investigation into input-based steering methods for context-aware reasoning. |
| title | Chain-of-Thought Augmentation with Logit Contrast for Enhanced Reasoning in Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.03600 |