Papers › Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in...

Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models

21 Aug 2024arXiv:2408.11252archive 2025-07-28

Sepehr Kamahi, Yadollah Yaghoobzadeh

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation method -- how accurately it explains the inner workings and decision-making of the model -- is challenging because it is difficult to separate the model from its explanation. Most faithfulness evaluation techniques corrupt or remove input tokens deemed important by a particular attribution (feature importance) method and observe the resulting change in the model's output. However, for autoregressive language models, this approach creates out-of-distribution inputs due to their next-token prediction training objective. In this study, we propose a technique that leverages counterfactual generation to evaluate the faithfulness of attribution methods for autoregressive language models. Our technique generates fluent, in-distribution counterfactuals, making the evaluation protocol more reliable.

PaperPDFCode

Code

sepehr-kamahi/faith officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decision MakingFeature ImportanceLanguage Modelling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Counterfactuals

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections