Papers with post hoc explanation methods

1 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations