AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Fairness Perceptions of Large Language Models

Benjamin Cookson, Soroush Ebadian, Nisarg Shah

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Bias measurement and mitigation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
ask LLM to be fair (default prompt) vs MNW baselineGPT-4o, Claude-3.5-Sonnet, Gemini-1.5-Pro · Synthetic fair divisionEF1 vs SW approximation: EF1 17-36% vs MNW 100%; SW 92-94% vs 86%Hurt
increase utility variation lambdaLLMs (default prompt) · Synthetic fair divisionEF1 approximationHurt
change allocation context to Sibling/Heirloom or Team/Machine (ablation)LLMs · Synthetic fair divisionEF1 approximationNo clear effect
present valuations grouped by goods (Object/Person) (ablation)Claude and Gemini · Synthetic fair divisionEF1 approximation / SW: lower EF1, higher SWMixed
present valuations grouped by goods (Object/Person) (ablation)GPT-4o · Synthetic fair divisionEF1 and SW approximationNo clear effect
prompt explicitly for EF1 fairness instead of 'fair' (ablation)LLMs · Synthetic fair divisionEF1 approximationImproved
frame EF1 as purely combinatorial problem without fairness language (ablation)GPT and Gemini · Synthetic fair division (varying lambda)EF1 approximationImproved
frame EF1 as purely combinatorial problem (ablation)Claude · Synthetic fair division (varying lambda)EF1 approximationNo clear effect
use real Spliddit instances instead of synthetic onesLLMs · Spliddit.orgEF1 approximationImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy