bias-correction

Tag

Cards List
#bias-correction

OrDA: Orthogonal Disentanglement of Access Habits Framework for Homepage Marketing Block Recommendations

arXiv cs.LG · 5d ago Cached

OrDA is a framework that disentangles user access habits from genuine content interests in homepage marketing block recommendations using orthogonal regularization and causal intervention, achieving a 5.64% UCTR improvement on Zhima's homepage.

0 favorites 0 likes
#bias-correction

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

arXiv cs.LG · 2026-06-29 Cached

This paper introduces Retroactive Advantage Correction (RAC), a closed-form bias correction method for delay-aware RLHF that handles asynchronous reward signals by queuing and reinjecting delayed rewards with a V-trace-style clipped residual update.

0 favorites 0 likes
#bias-correction

Recovering Stranded Discrimination in Knowledge Tracing: Per-Item Bias Correction via Empirical-Bayes Shrinkage

arXiv cs.LG · 2026-06-15 Cached

This paper introduces SLC (State-space Logit Correction), which corrects per-item logit bias in knowledge tracing models using empirical-Bayes shrinkage via a Kalman smoother, improving AUC beyond global calibration techniques.

0 favorites 0 likes
#bias-correction

Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference

arXiv cs.LG · 2026-06-05 Cached

This paper introduces PRECISE, an extension of Prediction-Powered Inference that combines a small set of human labels with a large set of LLM judgments to produce unbiased and variance-reduced estimates of ranking evaluation metrics like Precision@K. The method is validated on the ESCI benchmark and in a production A/B test, where it correctly identified the best system variant using only 100 human labels, confirmed by a +407 bps sales improvement.

0 favorites 0 likes
#bias-correction

Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion

arXiv cs.LG · 2026-05-27 Cached

This paper identifies a bias in attention weights caused by quantizing keys in KV-cache compression for chunk-wise autoregressive video diffusion, and proposes a per-attention-score correction that removes the bias with negligible overhead, recovering near-BF16 video quality at INT2 quantization.

0 favorites 0 likes
#bias-correction

On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach

arXiv cs.LG · 2026-05-27 Cached

This paper presents PushCen-ADFL, a communication-efficient asynchronous decentralized federated learning framework that uses centroid-based messaging and bias-correction to improve accuracy and reduce communication overhead under heterogeneous conditions.

0 favorites 0 likes
← Back to home

Submit Feedback