AI Paper Atlas

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

Bias Association Discovery Framework for Open-Ended LLM Generations

Jinhao Pan, Chahat Raj, Ziwei Zhu

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Bias measurement and mitigation · 3 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
use Negative sentiment-constrained prompt instead of two-character base prompt (ablation)BADF generation · Gender (Female), Llama3.2-3Bnumber of bias associations: 277 -> 524Improved
use Balanced-Valence prompt instead of two-character base prompt (ablation)BADF generation · Gender (Female), Llama3.2-3Bnumber of bias associations: 277 -> 423Improved
use open-box (patchscope) generation instead of black-box (ablation)BADF generation · Gender (Female), Llama3.2-3Bnumber of bias associations: 277 -> 332Improved
use open-box (patchscope) generation instead of black-box (ablation)BADF generation · Religions, Llama3.2-3Bnumber of bias associations: Muslim 832 -> 318Hurt
use two-character instead of single-character base setting (ablation)BADF generation · Gender (Female), Llama3.2-3Bnumber of bias associations: 169 -> 277Improved
use Qwen3-8B instead of Llama3.2-3B as the generatorBADF generation · Gender (Male), two-character basenumber of bias associations: 167 -> 408Improved

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