Function Vectors in Large Language Models (2023 · 127 citations)
The paper asks whether autoregressive transformer LMs internally store an abstract representation of the task shown in in-context learning (ICL) prompts.
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis (2026 · 7 citations)
Research on mechanistic interpretability (MI) of language models is fragmented. Studies use bespoke evaluations, lack a shared theoretical basis, and rarely define the elementary causal units that make up a "mechanism." This survey, published in Computational Linguistics, treats MI as recovering causal graphs that…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Function Vectors in Large Language ModelsarXiv:2310.15213Eric Todd, Millicent L. Li, Arnab Sen Sharma, et al.2023 · 127 citations
The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation AnalysisComputational LinguisticsAaron Mueller, Jannik Brinkmann, Millicent Li, et al.2026 · 7 citations
Shared Lexical Task Representations Explain Behavioral Variability In LLMs ↗arXiv (Cornell University) · no summary yetZhuonan Yang et al.2026

Co-authors here

9 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 128 times (of the 149,439 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated 2 November 2026