Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning, Ye+, University of Science and Technology of China, SIGIR'23 #580

Open
AkihikoWatanabe opened this issue Apr 28, 2023 · 1 comment

Comments

@AkihikoWatanabe
Copy link
Owner

https://arxiv.org/abs/2301.13808

@AkihikoWatanabe
Copy link
Owner Author

AkihikoWatanabe commented Apr 28, 2023

テーブルとquestionが与えられた時に、questionをsub-questionとsmall tableにLLMでin-context learningすることで分割。subquestionの解を得るためのsqlを作成しスポットを埋め、hallucinationを防ぐ。最終的にLLM Reasonerが解答を導出する。TabFact Reasoningで初めて人間を超えた性能を発揮。

image

@AkihikoWatanabe AkihikoWatanabe changed the title Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning, Ye+, University of Science and Technology of China, SIGIR'23 Apr 28, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant