@inproceedings{d53cdfe2359f4fea824a965e76088953,
title = "RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations",
abstract = "Individual neurons participate in the representation of multiple high-level concepts. To what extent can different interpretability methods successfully disentangle these roles? To help address this question, we introduce RAVEL (Resolving Attribute-Value Entanglements in Language Models), a dataset that enables tightly controlled, quantitative comparisons between a variety of existing interpretability methods. We use the resulting conceptual framework to define the new method of Multi-task Distributed Alignment Search (MDAS), which allows us to find distributed representations satisfying multiple causal criteria. With Llama2-7B as the target language model, MDAS achieves state-of-the-art results on RAVEL, demonstrating the importance of going beyond neuron-level analyses to identify features distributed across activations. We release our benchmark at https://github.com/explanare/ravel.",
author = "Jing Huang and Zhengxuan Wu and Christopher Potts and Mor Geva and Atticus Geiger",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024 ; Conference date: 11-08-2024 Through 16-08-2024",
year = "2024",
language = "الإنجليزيّة",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "8669--8687",
editor = "Lun-Wei Ku and Martins, {Andre F. T.} and Vivek Srikumar",
booktitle = "Long Papers",
address = "الولايات المتّحدة",
}