Papers with post hoc explanation methods
Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Autoregressive Large Language Models (LLMs) have demonstrated "emergent abilities" such as in-context learning, instruction following and reasoning. |
| Approach: | They propose a method that generates rationales from post hoc explanation methods applied to small language models to improve their own performance. |
| Outcome: | The proposed method improves on four SLMs and five datasets with strong reasoning abilities. |