“you Are Grounded!”: Latent Name Artifacts In Pre-trained Language Models | Awesome LLM Papers Add your paper to Awesome LLM Papers

Awesome LLM Papers

A continuously updated collection of research papers on LLMs.

Stay Updated

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

"you Are Grounded!": Latent Name Artifacts In Pre-trained Language Models

Vered Shwartz, Rachel Rudinger, Oyvind Tafjord . Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020 – 46 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization EMNLP Ethics & Fairness Interdisciplinary Approaches Multimodal Semantic Representation Training Techniques

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.

Similar Work