debiasing

Tag

Cards List
#debiasing

SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages

arXiv cs.CL · 12h ago Cached

This paper audits multilingual clinical ASR systems on psychiatric interviews in Indian languages and proposes SamaVaani, a unified debiasing technique to improve performance and fairness across demographic groups.

0 favorites 0 likes
#debiasing

Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates

arXiv cs.LG · 2026-06-09 Cached

A post-hoc method reduces spurious correlations in fine-tuned LLMs by truncating the tail of the SVD of the weight update matrix. It reduces the spurious-group gap by up to 5x with less than 2pp accuracy loss, without retraining or group labels.

0 favorites 0 likes
#debiasing

PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation

arXiv cs.LG · 2026-05-22 Cached

PEARL introduces a contrastive percentile approximation framework to mitigate behavioral intensity imbalance in recommender systems, achieving significant gains in engagement metrics in a production livestream platform serving billions of users.

0 favorites 0 likes
#debiasing

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

arXiv cs.CL · 2026-05-18 Cached

DebiasRAG proposes a tuning-free, query-specific debiasing framework using retrieval-augmented generation to reduce social biases in LLMs without degrading their original capabilities.

0 favorites 0 likes
#debiasing

Solving the “Whac-a-mole dilemma”: A smarter way to debias AI vision models

MIT News — Artificial Intelligence · 2026-04-29 Cached

Researchers from MIT, WPI, and Google propose WRING, a novel post-processing debiasing method for Vision-Language Models that avoids the 'Whac-a-mole dilemma' of amplifying other biases when removing specific ones.

0 favorites 0 likes
#debiasing

Product-of-Experts Training Reduces Dataset Artifacts in Natural Language Inference

arXiv cs.CL · 2026-04-22 Cached

This paper proposes Product-of-Experts (PoE) training to reduce dataset artifacts in Natural Language Inference, downweighting examples where biased models are overconfident. PoE nearly preserves accuracy on SNLI (89.10% vs. 89.30%) while reducing bias reliance by ~4.85 percentage points.

0 favorites 0 likes
← Back to home

Submit Feedback