Anchored Alignment for Self-Explanations Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913550597881856 |
|---|---|
| author | Villa-Arenas, Luis Felipe Nizamoglu, Ata Wang, Qianli Möller, Sebastian Schmitt, Vera |
| author_facet | Villa-Arenas, Luis Felipe Nizamoglu, Ata Wang, Qianli Möller, Sebastian Schmitt, Vera |
| contents | In this work, we introduce a methodology for alignment designed to enhance the ability of large language models (LLMs) to articulate their reasoning (self-explanation) even in the absence of annotated rationale explanations. Our alignment methodology comprises three key components: explanation quality assessment, self-instruction dataset generation, and model alignment. Additionally, we present a novel technique called Alignment with Anchor Preference Pairs, which improves the selection of preference pairs by categorizing model outputs into three groups: consistently correct, consistently incorrect, and variable. By applying tailored strategies to each category, we enhance the effectiveness of Direct Preference Optimization (DPO). Our experimental results demonstrate that this approach significantly improves explanation quality while maintaining accuracy compared to other fine-tuning strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13216 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Anchored Alignment for Self-Explanations Enhancement Villa-Arenas, Luis Felipe Nizamoglu, Ata Wang, Qianli Möller, Sebastian Schmitt, Vera Artificial Intelligence Computation and Language In this work, we introduce a methodology for alignment designed to enhance the ability of large language models (LLMs) to articulate their reasoning (self-explanation) even in the absence of annotated rationale explanations. Our alignment methodology comprises three key components: explanation quality assessment, self-instruction dataset generation, and model alignment. Additionally, we present a novel technique called Alignment with Anchor Preference Pairs, which improves the selection of preference pairs by categorizing model outputs into three groups: consistently correct, consistently incorrect, and variable. By applying tailored strategies to each category, we enhance the effectiveness of Direct Preference Optimization (DPO). Our experimental results demonstrate that this approach significantly improves explanation quality while maintaining accuracy compared to other fine-tuning strategies. |
| title | Anchored Alignment for Self-Explanations Enhancement |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2410.13216 |