EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis

Aaron Mueller, Jannik Brinkmann, Millicent Li, Samuel Marks, Koyena Pal, Nikhil Prakash, Can Rager, Aruna Sankaranarayanan, Arnab Sen Sharma, Jiuding Sun, Eric Todd, David Bau und 1 weitere

Computational Linguistics · 01.03.2026 · 52 (1) · 331-378

DOI: 10.1162/coli.a.572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Linguistics, online erschienen am 01.03.2026. Verfasst von Aaron Mueller und 12 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 220 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interpretability provides a toolset for understanding how and why language models behave in certain ways. However, there is little unity in the field: Most studies use ad-hoc evaluations and do not share theoretical foundations, making it difficult to measure progress and compare the pros and cons of different techniques. Furthermore, while mechanistic understanding is frequently discussed, the basic causal units underlying these mechanisms are often not explicitly defined. In this article, we propose a perspective on interpretability research grounded in causal mediation analysis. Specifically, we describe the history and current state of interpretability taxonomized according to the types of causal units (mediators) utilized, as well as methods used to search over mediators. We discuss the pros and cons of each mediator, providing insights as to when particular kinds of mediators and search methods are most appropriate. We argue that this framing yields a more cohesive narrative of the field and helps researchers select appropriate methods based on their research objective. Our analysis yields actionable recommendations for future work, including the discovery of new mediators and the development of standardized evaluations tailored to these goals.

Zitieren

APA

Mueller, A., Brinkmann, J., Li, M., Marks, S., Pal, K., Prakash, N., Rager, C., Sankaranarayanan, A., Sharma, A. S., Sun, J., Todd, E., Bau, D., & Belinkov, Y. (2026). The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis. Computational Linguistics, 52(1), 331-378. https://doi.org/10.1162/coli.a.572

Vancouver

Mueller A, Brinkmann J, Li M, Marks S, Pal K, Prakash N, et al. The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis. Computational Linguistics. 2026;52(1):331-378. doi:10.1162/coli.a.572

BibTeX
@article{Mueller2026,
  author = {Mueller, Aaron and Brinkmann, Jannik and Li, Millicent and Marks, Samuel and Pal, Koyena and Prakash, Nikhil and Rager, Can and Sankaranarayanan, Aruna and Sharma, Arnab Sen and Sun, Jiuding and Todd, Eric and Bau, David and Belinkov, Yonatan},
  title = {The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation Analysis},
  journal = {Computational Linguistics},
  year = {2026},
  volume = {52},
  number = {1},
  pages = {331--378},
  doi = {10.1162/coli.a.572}
}
Kostenlos starten →