pith. sign in

InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11328– 11345, Singapore

Deciphering stereotypes in pre-trained language models · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Can We Locate and Prevent Stereotypes in LLMs?

cs.CL · 2026-03-26 · unverdicted · novelty 4.0

Exploratory study maps stereotype encodings to individual neurons and attention heads in two LLMs via contrastive activation analysis.

citing papers explorer

Showing 1 of 1 citing paper.

  • Can We Locate and Prevent Stereotypes in LLMs? cs.CL · 2026-03-26 · unverdicted · none · ref 3

    Exploratory study maps stereotype encodings to individual neurons and attention heads in two LLMs via contrastive activation analysis.