Abstract
With large language models surpassing human performance on an increasing number of benchmarks, we must take a principled approach for targeted evaluation of model capabilities. Inspired by pseudorandomness, we propose pseudointelligence, which captures the maxim that “(perceived) intelligence lies in the eye of the beholder.” That is, that claims of intelligence are meaningful only when their evaluator is taken into account. Concretely, we propose a complexity-theoretic framework of model evaluation cast as a dynamic interaction between a model and a learned evaluator. We demonstrate that this framework can be used to reason about two case studies in language model evaluation, as well as analyze existing evaluation methods.- Anthology ID:
- 2023.findings-emnlp.485
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7284–7290
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.485
- DOI:
- 10.18653/v1/2023.findings-emnlp.485
- Cite (ACL):
- Shikhar Murty, Orr Paradise, and Pratyusha Sharma. 2023. Pseudointelligence: A Unifying Lens on Language Model Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7284–7290, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Pseudointelligence: A Unifying Lens on Language Model Evaluation (Murty et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.485.pdf