Abstract
Work done to uncover the knowledge encoded within pre-trained language models rely on annotated corpora or human-in-the-loop methods. However, these approaches are limited in terms of scalability and the scope of interpretation. We propose using a large language model, ChatGPT, as an annotator to enable fine-grained interpretation analysis of pre-trained language models. We discover latent concepts within pre-trained language models by applying agglomerative hierarchical clustering over contextualized representations and then annotate these concepts using ChatGPT. Our findings demonstrate that ChatGPT produces accurate and semantically richer annotations compared to human-annotated concepts. Additionally, we showcase how GPT-based annotations empower interpretation analysis methodologies of which we demonstrate two: probing frameworks and neuron interpretation. To facilitate further exploration and experimentation in the field, we make available a substantial ConceptNet dataset (TCN) comprising 39,000 annotated concepts.- Anthology ID:
- 2023.emnlp-main.196
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3248–3268
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.196
- DOI:
- 10.18653/v1/2023.emnlp-main.196
- Cite (ACL):
- Basel Mousi, Nadir Durrani, and Fahim Dalvi. 2023. Can LLMs Facilitate Interpretation of Pre-trained Language Models?. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3248–3268, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Can LLMs Facilitate Interpretation of Pre-trained Language Models? (Mousi et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.196.pdf