arXiv Machine Learning September 18, 2026 By Dang Quang Minh, Nguyen Dung Son, Nguyen Huu Loi, Truong Viet Vu, Nguyen Thai Anh

Accuracy Is Not Enough: A Cross-Architecture Audit of Demographic Bias in Deep Knowledge Tracing

Read the original on arXiv Machine Learning →

The study audits demographic bias across four deep knowledge tracing architectures—DKT, DKVMN, SAKT, and AKT—using two large public datasets (Eedi and OULAD). It finds that bias is context‑dependent: socioeconomic bias is significant on Eedi, while gender bias appears on OULAD for most models. The most accurate model, AKT, also exhibits the greatest bias, and standard mitigation techniques such as reweighting and adversarial debiasing fail to reduce bias without sacrificing accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 16

Not All Skills Help: Measuring and Repairing Agent Knowledge

arXiv:2606. 15390v1 Announce Type: cross Abstract: LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone.

By Yixuan Wang, Yiyang Zhou, Yiming Liang, Congyu Zhang, Fuxiao Liu, Jiawei Zhou, Huaxiu Yao

llms agents benchmarks

arXiv Machine Learning

Sep 1

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

arXiv:2601.03087v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM...

By David Hartmann, Lena Pohlmann, Lelia Hanslik, Noah Gie{\ss}ing, Bettina Berendt, Pieter Delobelle

llms safety

arXiv Machine Learning

Aug 10

Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs

arXiv:2509. 16462v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities.

By Mina Arzaghi, Alireza Dehghanpour Farashah, Florian Carichon, Jean-Fran\c{c}ois Plante, Golnoosh Farnadi

llms rag fine-tuning benchmarks safety

arXiv AI

Jun 2

Fair Finetuning Mitigates Distribution Inference Attacks

arXiv:2606. 01719v1 Announce Type: cross Abstract: Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference attack (DIA).

By Rakshit Naidu

nlp fine-tuning safety

arXiv Machine Learning

4d ago

When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels

arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising $97\%$ cost reductions over traditional surveys. Yet aggregat...

By Robson Tigre, Hugo Gobato Souto

llms safety

arXiv Machine Learning

Jul 31

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).

By Pere Martra, Eugenio Mart\'inez C\'amara, Alfonso Ure\~na L\'opez

llms efficiency benchmarks safety

One email a morning, machine-written

Related stories

Not All Skills Help: Measuring and Repairing Agent Knowledge

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs

Fair Finetuning Mitigates Distribution Inference Attacks

When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations