Abstract
We introduce the CRASS (counterfactual reasoning assessment) data set and benchmark utilizing questionized counterfactual conditionals as a novel and powerful tool to evaluate large language models. We present the data set design and benchmark. We test six state-of-the-art models against our benchmark. Our results show that it poses a valid challenge for these models and opens up considerable room for their improvement.- Anthology ID:
- 2022.lrec-1.229
- Volume:
- Proceedings of the Thirteenth Language Resources and Evaluation Conference
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 2126–2140
- Language:
- URL:
- https://aclanthology.org/2022.lrec-1.229
- DOI:
- Cite (ACL):
- Jörg Frohberg and Frank Binder. 2022. CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2126–2140, Marseille, France. European Language Resources Association.
- Cite (Informal):
- CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models (Frohberg & Binder, LREC 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.lrec-1.229.pdf