FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software
Source
Archit Rathod, Saeid Tizpaz-Niari
Author
Archit Rathod, Saeid Tizpaz-Niari
Date
Why it matters
FairLint-DL is a VS Code extension that runs fairness debugging on tabular datasets before training starts, using entropy-based discrimination metrics and gradient-guided search to localize bias to specific layers and neurons.
articleBias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier ModelsWilliam Guey, Pierrick Bougault, Wei Zhang, Vitor D. de Moura, Jos\'e O. Gomes
articleDiagnostic Foundation for Evaluating LLMs' Research Integrity as Co-ScientistsYash Tripathi, Silu Sharma, Sai Sidhanth Manoharan Jayanthi, Shivank Garg, Lin Li
articleTesting Deep Learning Library APIs via Cross-Framework Differential FuzzingBin Duan, Ruican Dong, Naipeng Dong, Dan Dongseong Kim, Guowei Yang