Papers › CHILLI: A data context-aware perturbation method for XAI

CHILLI: A data context-aware perturbation method for XAI

10 Jul 2024arXiv:2407.07521archive 2025-07-28

Saif Anwar, Nathan Griffiths, Abhir Bhalerao, Thomas Popham

The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision is opaque to the user. To address this, some existing Explainable AI (XAI) approaches approximate model behaviour using perturbed data. However, such methods have been criticised for ignoring feature dependencies, with explanations being based on potentially unrealistic data. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations, which are faithful to the training data of the base model being explained. This is shown to improve both the soundness and accuracy of the explanations.

PaperPDFCode

Code

saiffanwar/MASALA mentioned 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.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AWAREBASE

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