Implicit Bias

Follow this topic Ask about this topic

Recent momentum

-12%

29 papers in the last 28 days · 0.5% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Implicit Bias.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Implicit Bias.

Period ending 2026-09-07

4 new papers

A weekly snapshot of new work published in Implicit Bias.

320 papers

Latest in Implicit Bias

Browse all topics →

Reducing Political Manipulation with Consistency Training
May 21, 2026Long Phan, Devin Kim, Alexander Pan +3Ideology Large Language Model Bias
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
May 21, 2026David Mendez, Fernando Martin-Maroto, Gonzalo G. de PolaviejaMachine Learning Convolutional Neural Networks
SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals
May 21, 2026Zihang Lin, Huaiyuan Qin, Muli Yang +1Large Vision Language Models Large Language Model Bias
Mitigating Label Bias with Interpretable Rubric Embeddings
May 20, 2026Calvin Isley, Johann D. Gaebler, Sharad GoelImplicit Bias
Semiparametric Efficient Bilevel Gradient Estimation
May 20, 2026Fares El Khoury, Houssam Zenati, Nathan Kallus +2Bilevel Optimization Semiparametric Framework
Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection
May 20, 2026Mathieu Cherpitel, Thomas Bäck, Martijn R. Tannemaat +1Feature Selection Principal Component Analysis
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
May 20, 2026Ishaan Kelkar, Nebras Alam, Vikram Kakaria +3Sycophancy Persona
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
May 19, 2026Jingwen Liu, Ezra Edelman, Surbhi Goel +1Unified Inductive Bias Table Reasoning Datasets
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
May 19, 2026Reza M. Asiyabi, Juan Alberto Molina-Valero, The SEOSAW Partnership +2Above-Ground Biomass Logistic Regression
Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
May 19, 2026Xinpeng Lv, Yunxin Mao, Renzhe Xu +11Rationality Implicit Bias
Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning
May 19, 2026Tom Jacobs, Guido MontufarFeature Learning Gradient Flow
DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs
May 19, 2026Minyoung Park, Taehun Kong, Sangjun AhnToken Compression Textvqa
Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
May 18, 2026Zhilin Zhu, Yabin Wang, Zhiheng Ma +3Continual Test-Time Adaptation Domain Shift
OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models
May 18, 2026Chiara Maria Russo, Simone Carnemolla, Simone Palazzo +3Vision Foundation Models Image Classification
CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models
May 18, 2026Reem Alzahrani, Hassan Alshanqiti, Bushra Bin Hemid +3Counting Multimodal Reasoning
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
May 17, 2026Anvesh Rao Vijjini, Sagar Manjunath, Snigdha ChaturvediLarge Language Model Bias Personalized Large Language Model Agents
To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
May 16, 2026Wei Shi, Ziheng Peng, Sihang Li +4Call Large Language Model Agents
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation
May 15, 2026Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6Large Language Model Bias Implicit Bias
Unsupervised Domain Shift Detection with Interpretable Subspace Attribution
May 15, 2026Sebastian Springer, Alessandro LaioCross-Domain Shifts Domain Shift
Learning with Conflicts of Interest
May 15, 2026Nischal Aryal, Arash Termehchy, Ali Vakilian +1Game Theory Implicit Bias
Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment
May 14, 2026Fan Yin, Chuhang Zheng, Peiliang Gong +2Electroencephalography Spatial Super-Resolution Visual Reasoning
Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines
May 14, 2026Federico Germani, Giovanni SpitaleSycophancy Artificial Intelligence Literacy
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
May 14, 2026Yiheng Li, Yang Yang, Zichang Tan +3Ai-Generated Image Detection Forgeries
Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling
May 13, 2026Deepak Pandita, Flip Korn, Chris Welty +1Reproducibility Large Language Model Evaluation
A $_3$ B $_2$ : Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
May 13, 2026Yiyun Zhou, Zhonghua Jiang, Wenkang Han +4Vision-Language Model Adaptation Few-Shot Learning
Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
May 13, 2026Runlong Xie, An LuoFourier Neural Operators Neural Operators
What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind
May 12, 2026Patrick Callaghan, Reid Simmons, Henny AdmoniTheory-Of-Mind Reasoning Belief
Assessment of cloud and associated radiation fields from a GAN stochastic cloud subcolumn generator
May 12, 2026Dongmin Lee, Lazaros Oreopoulos, Nayeong Cho +1Generative Adversarial Network Generators
What Does It Mean for a Medical AI System to Be Right?
May 12, 2026Antony GitauModel Interpretability Correctness
DiffScore: Text Evaluation Beyond Autoregressive Likelihood
May 12, 2026Wen Lai, Yingli Shen, Dingnan Jin +4Implicit Bias
Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration
May 12, 2026Mingtao Xian, Yifeng Yang, Qinying Gu +2Multi-Modal Large Language Models Cross-Modal Attention
Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
May 11, 2026Ege C. Kaya, Aliasghar Pourghani, Vijay Gupta +1Representation Space Implicit Bias
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
May 11, 2026Eduardo Tenorio, Karuna Bhaila, Xintao WuLarge Language Model Bias Differential Privacy
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
May 11, 2026Christian Moya, Alex Semendinger, Guang Lin +1Preference Learning Direct Preference Optimization
Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring
May 11, 2026Jiaqing Zhang, Sandeep Elluri, Bhanu Cherukuvada +7Mean Opinion Scores Llm-As-A-Judge
Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks
May 11, 2026Regina Gugg, Selina Niederländer, Andreas Stöckl +1Large Language Model Evaluation Toxicity
Can Muon Fine-tune Adam-Pretrained Models?
May 11, 2026Xingyu Qu, Peigeng Huang, Samuel HorvathAdam Muon
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
May 11, 2026Pierre Le Jeune, Étienne Duchesne, Weixuan Xiao +4Stereotype Mitigation Implicit Bias
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
May 11, 2026Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3Efficient Long-Context Inference Bilevel Optimization
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
May 11, 2026Gideon Popoola, John SheppardExplainable Artificial Intelligence Implicit Bias
Primal-Dual Guided Decoding for Constrained Discrete Diffusion
May 10, 2026Federico Tomasi, Dmitrii Moor, Alice Wang +1Discrete Diffusion Model Diffusion Processes
Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven
May 10, 2026Jiwei Tang, Zhijing Huang, Xinyu Zhang +5Large Language Model Compression Efficient Long-Context Inference
Let the Target Select for Itself: Data Selection via Target-Aligned Paths
May 10, 2026Huitao Yang, Hengzhi He, Guang ChengTraining Data Attribution Adaptive Sampling
The Pokémon Theorem and other Fairness Impossibility Results
May 9, 2026Daniel Matsui Smola, Alex SmolaFairness Constraints Implicit Bias
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
May 9, 2026Weidong Zheng, Kongyang Chen, Yuanwei Guo +1Bias Mitigation Implicit Bias
Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation
May 9, 2026Jikun Wu, Dongxin Guo, Siu-Ming YiuImplicit Bias Cognitive Science
Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies
May 8, 2026Muyun Lu, Haoyang Hong, Huazheng Wang +1Multi-Armed Bandits Generalized Linear Bandit
Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
May 8, 2026Bruno Bianchi, Diego Tiscornia, Matias Travizano +1Large Language Model Bias Ideology
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
May 8, 2026Taein Lim, Seongyong Ju, Munhyeok Kim +2Implicit Bias Large Language Model Agents
Causal EpiNets: Precision-corrected Bounds on Individual Treatment Effects using Epistemic Neural Networks
May 8, 2026Gandharv Patil, Keyi Tang, Raquel Aoki +1Heterogeneous Treatment Effects Finite-Sample
Mitigating Cognitive Bias in RLHF by Altering Rationality
May 7, 2026Tiffany Horter, Andrew Markham, Niki Trigoni +1Reinforcement Learning From Human Feedback Rationality
Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
May 7, 2026Aditya Parikh, Stella Frank, Sneha Das +1Bias Mitigation Implicit Bias
Debiased Multimodal Personality Understanding through Dual Causal Intervention
May 7, 2026Yangfu Zhu, Zitong Han, Nianwen Ning +4Personality Causal Intervention
When Does $\ell_2$ -Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\ell_1$ Implicit Bias
May 7, 2026Ye Su, Jian Li, Yong LiuOverfitting Empirical Risk Minimization
The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
May 7, 2026Hoin Jung, Xiaoqian WangMulti-Source Retrieval-Augmented Generation Multi-Modal Large Language Models
Estimating Implicit Regularization in Deep Learning
May 6, 2026Joseph H. Rudoler, Kevin Tan, Giles Hooker +1Regularization Techniques Quadratic Slack Penalty
Misaligned by Reward: Socially Undesirable Preferences in LLMs
May 6, 2026Gayane Ghazaryan, Esra DönmezLarge Language Model Alignment Large Language Model Bias
Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africa
May 5, 2026Hoffmann Muki, Olukunle OwolabiConflict Humanitarian Reports
Magic-Informed Quantum Architecture Search
May 5, 2026Vincenzo Lipardi, Domenica Dibenedetto, Georgios Stamoulis +1Quantum Advantage Many-Body Physics
Predicting missing values: A good idea?
May 5, 2026Stef van BuurenMultivariate Time Series Imputation Missing Data

May 21, 2026 · cs.CLJ/K move · Enter open · S save

Reducing Political Manipulation with Consistency Training

Long Phan, Devin Kim, Alexander Pan, Alice Blair+2

Center for AI Safety · UC Berkeley

Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political prompts; Helpfulness Consistency measures symmetric depth and engagement. To reduce both types of covert bias, we introduce Political Consistency Training (PCT), an RL training method with two complementary paradigms: Sentiment Consistency Training and Helpfulness Consistency Training. We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks. We release our work at https://political-manipulation.ai

Ideology Large Language Model Bias Implicit Bias Large Language Model Alignment

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

12 new papers

3 new papers

4 new papers

Latest in Implicit Bias