Paper

How Reliable are Fairness Audits with Unreliable Data?

Unreadunread

AI summary

arXiv:2506. 23033v4 Announce Type: replace-cross Abstract: Fairness audits are a key component of responsible machine-learning deployment.

Reading status

Priority

About this paper

Authors: Yash Vardhan Tomar
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because How Reliable are Fairness Audits with Unreliable Data? overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, under, line, rate, candidates, candidate, test. Source: arxiv stat.ML (Machine Learning).
arXiv: 2506.23033

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to How Reliable are Fairness Audits with Unreliable Data?. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.