AI Paper Atlas

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

SCoUT: A Framework for Structured Stereotype Analysis in Language Models

Jinxuan Wu, Bin Li, Xiangyang Xue

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Pruning and circuits in LLMs · 0 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
add reasoning prompt (ablation)SCoUT on DeepSeek-7B · Warmth preference predictionaccuracy (%): 68.8 ± 6.3 -> 84.4 ± 4.6 (+15.6)Improved
add reasoning prompt (ablation)SCoUT on DeepSeek-7B · Competence preference predictionaccuracy (%): 74.7 ± 5.3 -> 87.8 ± 3.8 (+13.1)Improved
add reasoning prompt (ablation)SCoUT on DeepSeek-67B · Warmth preference predictionaccuracy (%): 74.7 ± 5.7 -> 89.5 ± 3.8 (+14.8)Improved
add reasoning prompt (ablation)SCoUT on Qwen2.5-7B · Warmth preference predictionaccuracy (%): 79.3 ± 5.7 -> 84.8 ± 4.6 (+5.5)Improved
add reasoning prompt (ablation)SCoUT on Qwen2.5-7B · Competence preference predictionaccuracy (%): 90.3 ± 3.8 -> 89.5 ± 3.6 (-0.8)Hurt
add reasoning prompt (ablation)SCoUT on LLaMA3.1-70B · Warmth preference predictionaccuracy (%): 95.8 ± 2.3 -> 95.4 ± 2.7 (-0.4)No clear effect
add reasoning prompt (ablation)SCoUT on LLaMA3.1-8B · Competence preference predictionaccuracy (%): 90.3 ± 3.8 -> 90.7 ± 3.6 (+0.4)No clear effect
use larger modelSCoUT on DeepSeek · Competence preference predictionaccuracy (%): 74.7 ± 5.3 -> 86.9 ± 4.2Improved
replace direct Likert scoring (Stereomap) with Thurstonian comparative modelingStereomap · Warmth score distributionrange of scores: [-2.0, 1.67] -> [-2.53, 2.17]Improved
steer attention heads with alpha=-30 (negative)LLaMA3.3-70B · Professor review taskcommunal score: 57.54 -> 40.44 (-17.10)Improved
steer attention heads with alpha=+30 (positive)LLaMA3.3-70B · Professor review taskcommunal score: 57.54 -> 86.71 (+29.17)Improved
steer Hispanic male subgroup with alpha=-30LLaMA3.3-70B · Professor review task (Hispanic Male)communal score: 49.38 -> 57.02 (+7.65)Hurt

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