{"total":20,"rows":[{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2605.20745","title":"The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering","created":"2026-05-20","cited_by_count":5,"area":null},{"id":"2510.00232","title":"BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2608.11735","title":"Locating and Controlling Implicit Personalization in Large Language Models","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2506.12527","title":"Detection, Classification, and Mitigation of Gender Bias in Large Language Models","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2508.08855","title":"BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2601.12868","title":"Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.00300","title":"Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2607.27824","title":"STEREODISCO: Discovering Stereotypicality in LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2510.10142","title":"Debiasing LLMs by Masking Unfairness-Driving Attention Heads","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2601.21864","title":"Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2608.22852","title":"Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.01081","title":"StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.24228","title":"IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.40124","title":"Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15961","title":"Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}