True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4
Authors:
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 314-322
Abstract
Maksym Del, Mark Fishel. Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023). 2023.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- BiQuAD: Towards QA based on deeper text understanding2021
- SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference2018
- A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference2018
- A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories2016
- A large annotated corpus for learning natural language inference2015