Abstract
Pre-trained language models (LMs) may perpetuate biases originating in their training corpus to downstream models. We focus on artifacts associated with the representation of given names (e.g., Donald), which, depending on the corpus, may be associated with specific entities, as indicated by next token prediction (e.g., Trump). While helpful in some contexts, grounding happens also in under-specified or inappropriate contexts. For example, endings generated for ‘Donald is a’ substantially differ from those of other names, and often have more-than-average negative sentiment. We demonstrate the potential effect on downstream tasks with reading comprehension probes where name perturbation changes the model answers. As a silver lining, our experiments suggest that additional pre-training on different corpora may mitigate this bias.- Anthology ID:
- 2020.emnlp-main.556
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6850–6861
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.556
- DOI:
- 10.18653/v1/2020.emnlp-main.556
- Cite (ACL):
- Vered Shwartz, Rachel Rudinger, and Oyvind Tafjord. 2020. “You are grounded!”: Latent Name Artifacts in Pre-trained Language Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6850–6861, Online. Association for Computational Linguistics.
- Cite (Informal):
- “You are grounded!”: Latent Name Artifacts in Pre-trained Language Models (Shwartz et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.556.pdf