Team Credits and Caveats: Fairness Labels Are Sensitive, Disparities Vary Widely
mundt_martin · x · 2026-10-25
Posts #4-5 of the same thread: the authors note the results call for new continual learning methods that account for social outcomes when balancing stability and plasticity — easier said than done, since disparities differ across groups, methods, and datasets, and demographic labels are sensitive (used only for testing).
Post #5 credits collaborators: Kajaree Das as lead author (her first paper in the lab), with Oliver Böse, Subarnaduti Paul, and Gabriel Storch; paper and code links are public.
More from Research
- Debate: could exponential compute replace wet-lab experiments in biology? — cjmaddison · 2026-10-26
- LLMs are obsessed with Japan: 24-language study traces cultural bias to SFT — alex_verem · 2026-10-26
- Top-b sampling: entropy-adaptive decoding beats Top-p on GPQA and cuts variance 10x — cneuralnetwork · 2026-10-26
- MathDB launches as an open platform for AI-era math research with Lean support — lpachter · 2026-10-26
- ConformWeb: LLM-generated web apps pass only 11.7% of behavioral contract checks — algo_diver · 2026-10-26
- Claude runs 53 hours unsupervised, beats human designs on 7 of 8 quantum problems — FinanceYF5 · 2026-10-26