Trusted-AI / Trusted-AI/AIX360

Faithfulness metric on imags explanations

Open
#99 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.8k
Forks
327
Avg merge
1h 13m
Merged PRs (30d)
1

Description

Can the faithfulness metric can be used as a metric for explanations obtained using LIME or SHAP.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the existing faithfulness metric and how LIME and SHAP explanations are represented in the project. Define whether the metric applies to both explanation methods, identify the expected behavior, and add coverage demonstrating the supported cases.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.