Abstract
While Large Language Models (LLMs) excel at the Winograd Schema Challenge (WSC), a coreference resolution task testing common-sense reasoning through pronoun disambiguation, they struggle with instances that feature minor alterations or rewording. To address this, we introduce EvoGrad, an open-source platform that harnesses a human-in-the-loop approach to create a dynamic dataset tailored to such altered WSC instances. Leveraging ChatGPT’s capabilities, we expand our task instances from 182 to 3691, setting a new benchmark for diverse common-sense reasoning datasets. Additionally, we introduce the error depth metric, assessing model stability in dynamic tasks. Our results emphasize the challenge posed by EvoGrad: Even the best performing LLM, GPT-3.5, achieves an accuracy of 65.0% with an average error depth of 7.2, a stark contrast to human performance of 92.8% accuracy without perturbation errors. This highlights ongoing model limitations and the value of dynamic datasets in uncovering them.- Anthology ID:
- 2024.lrec-main.592
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 6701–6716
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.592
- DOI:
- Cite (ACL):
- Jing Han Sun and Ali Emami. 2024. EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6701–6716, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries (Sun & Emami, LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.592.pdf