AIBearisharXiv – CS AI · Jun 17/10
🧠Researchers discovered that vision-language models suppress female representations in their outputs when processing ambiguous images, despite internally encoding female associations. The study introduces LALS, a new metric revealing that models systematically filter out female signals before generation while amplifying male signals, indicating a critical gap between internal model knowledge and biased outputs.
AINeutralarXiv – CS AI · May 287/10
🧠Researchers introduced MIRA, a bilingual benchmark testing whether large language models provide consistent medical information across different user phrasings, health literacy levels, and languages. The study revealed that LLMs systematically omit key medical details when responding to low-health-literacy queries, a pattern termed Differential Information Dilution (DID), with implications for equitable health information access.
🧠 Claude
AIBearisharXiv – CS AI · May 287/10
🧠Researchers demonstrate that biases in multi-agent AI systems can amplify at the system level rather than cancel out, with uniformly biased agents producing fairness degradation exceeding the sum of individual biases. The study introduces Favor Bias Strength (FBS), a metric to measure bias alteration, and reveals critical vulnerabilities in fairness preservation across deployed multi-agent systems.
AIBearisharXiv – CS AI · May 287/10
🧠A new academic framework argues that AI systems create an 'illusion of opting'—where users appear to have meaningful choice while their actual decision-making agency is systematically weakened. The research proposes three normative imperatives (existential honesty, ecological rationality, and counterfactual reparation) to protect human agency in AI-mediated consequential decisions, particularly for vulnerable populations.
AIBearisharXiv – CS AI · May 287/10
🧠A controlled study of instruction-tuned language model agents reveals they exhibit human-like in-group bias in multi-agent simulations, showing measurable discrimination based on group labels that accumulates into structural inequality over time. The bias operates subtly through resource allocation decisions rather than explicit negative actions, making it difficult to detect through standard auditing methods.
AIBearisharXiv – CS AI · May 127/10
🧠A comprehensive empirical study reveals that weight pruning—a technique for compressing large language models for edge devices—paradoxically amplifies bias while preserving performance metrics. The research shows activation-aware pruning methods maintain perplexity but increase stereotype reliance by up to 84%, suggesting current evaluation methods fail to detect fairness degradation in compressed models.
🏢 Perplexity
AIBearisharXiv – CS AI · May 117/10
🧠Research reveals that AI models, particularly few-shot large language models, struggle significantly with mid-range quality responses in automated short answer scoring, while fine-tuned models and human experts maintain consistent performance across all quality levels. This degradation raises fairness concerns for students with developing understanding, emphasizing the need for quality-conditioned evaluation metrics.
🧠 GPT-4🧠 GPT-5🧠 Claude
AIBearisharXiv – CS AI · Apr 147/10
🧠Researchers have conducted a comprehensive study examining how large vision-language models (LVLMs) exhibit cultural stereotypes and biases when making judgments about people's moral, ethical, and political values based on cultural context cues in images. Using counterfactual image sets and Moral Foundations Theory, the analysis across five popular LVLMs reveals significant concerns about AI fairness beyond traditional social biases, with implications for deployed AI systems used globally.
AIBearisharXiv – CS AI · Apr 147/10
🧠Researchers systematically analyzed how leading LLMs (GPT-4o, Llama-3.3, Mistral-Large-2.1) generate demographically targeted messaging and found consistent gender and age-based biases, with male and youth-targeted messages emphasizing agency while female and senior-targeted messages stress tradition and care. The study demonstrates how demographic stereotypes intensify in realistic targeting scenarios, highlighting critical fairness concerns for AI-driven personalized communication.
🧠 GPT-4🧠 Llama
AIBearisharXiv – CS AI · Apr 147/10
🧠Researchers evaluated four omnimodal AI models across text, image, audio, and video processing, finding substantial demographic and linguistic biases particularly in audio understanding tasks. The study reveals significant accuracy disparities across age, gender, language, and skin tone, with audio tasks showing prediction collapse toward narrow categories, highlighting fairness concerns as these models see wider real-world deployment.
AIBullisharXiv – CS AI · Mar 177/10
🧠Justitia is a new scheduling system for task-parallel LLM agents that optimizes GPU server performance through selective resource allocation based on completion order prediction. The system uses memory-centric cost quantification and virtual-time fair queuing to achieve both efficiency and fairness in LLM serving environments.
🏢 Meta
AIBullisharXiv – CS AI · Mar 177/10
🧠Researchers developed FairMed-XGB, a machine learning framework that reduces gender bias in healthcare AI models by 40-72% while maintaining predictive accuracy. The system uses Bayesian optimization and explainable AI to ensure equitable treatment decisions in critical care settings.
AIBearisharXiv – CS AI · Mar 177/10
🧠A comprehensive study of six major LLM families reveals systematic biases in moral judgments based on gender pronouns and grammatical markers. The research found that AI models consistently favor non-binary subjects while penalizing male subjects in fairness assessments, raising concerns about embedded biases in AI ethical decision-making.
🏢 Meta🧠 Grok
AINeutralarXiv – CS AI · Mar 127/10
🧠Research examining five major LLMs found they exhibit human-like cognitive biases when evaluating judicial scenarios, showing stronger virtuous victim effects but reduced credential-based halo effects compared to humans. The study suggests LLMs may offer modest improvements over human decision-making in judicial contexts, though variability across models limits current practical application.
🧠 ChatGPT🧠 Claude🧠 Sonnet
AINeutralarXiv – CS AI · Mar 57/10
🧠A comprehensive study analyzed four major large language models (LLMs) across political, ideological, alliance, language, and gender dimensions, revealing persistent biases despite efforts to make them neutral. The research used various experimental methods including news summarization, stance classification, UN voting patterns, multilingual tasks, and survey responses to uncover these systematic biases.
CryptoNeutralNewsBTC · Jun 236/10
⛓️An Ethereum Foundation executive has highlighted MEV (maximal extractable value) as an emerging battleground in cryptocurrency, framing the issue as the next major cypherpunk fight. This signals growing institutional concern about MEV's impact on blockchain fairness and decentralization.
$ETH
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers have released UnBias-Plus, an open-source toolkit designed to detect, explain, and rewrite bias in natural language across human-written and AI-generated content. The platform offers multi-class bias classification, span localization, neutral text rewriting, and interpretable reasoning, addressing a significant gap in bias mitigation tools with publicly available models and multiple interface options.
DeFiNeutralNewsBTC · Jun 196/10
💎Arbitrum governance is considering a paid Fast Feed proposal that would grant early access to ordered transaction metadata on Arbitrum One. This monetization initiative aims to generate revenue while creating a tiered access model for transaction data, potentially affecting MEV dynamics and user costs on the network.
$ARB
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers propose PAFO, a Pareto fairness optimization framework that addresses bias in personalized reward models for large language models by improving performance for under-served user preference groups without degrading majority groups. The method uses group-specialized models and conditional margin-level supervision to create fairer LLM alignment across diverse user populations.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce DIVERGE, a new retrieval-augmented generation (RAG) framework that addresses a critical limitation in current AI systems: their inability to generate diverse, multiple perspectives for open-ended questions. The system achieves approximately 2x greater diversity in outputs without sacrificing quality by using iterative reflection and diversity-aware retrieval strategies.
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers propose a novel framework that treats algorithmic bias as a symmetry-breaking problem, using loss-based regularization to enforce fairness constraints. The approach achieves over 90% violation reduction with minimal accuracy trade-offs while remaining computationally lightweight and not requiring causal graph knowledge.
🏢 Meta
AIBullisharXiv – CS AI · Jun 46/10
🧠Researchers introduce BiasGRPO, a novel framework using Group Relative Policy Optimization to mitigate social bias in Large Language Models more effectively than existing methods. The approach stabilizes training in high-variance reward landscapes by normalizing rewards across sampled completions, outperforming Direct Preference Optimization and Proximal Policy Optimization while maintaining computational efficiency.
AINeutralarXiv – CS AI · Jun 46/10
🧠Researchers introduce Adaptive Calibration (AC), a novel technique that improves facial recognition systems by mapping cosine similarity to well-calibrated probabilities while accounting for regional variations in embedding space. The method achieves better accuracy and fairness metrics without requiring demographic metadata, addressing a fundamental limitation where identical distances can represent different match probabilities across different regions.
🏢 Meta
AIBearisharXiv – CS AI · Jun 36/10
🧠Researchers evaluated demographic bias in skin lesion classification models, finding that sex biases stem primarily from data imbalances while age biases consistently favor younger populations regardless of training distribution. Multi-task and adversarial learning strategies showed limited effectiveness in male-majority datasets, highlighting the need for targeted bias mitigation approaches in medical AI systems.
AIBearisharXiv – CS AI · Jun 26/10
🧠Researchers examined how Text-to-Image AI models perpetuate caste biases in South Asian contexts, shifting analysis from treating caste as a static identity category to understanding it as a relational system. Using algorithmic audits and critical discourse analysis, they propose an anti-caste framework to address fairness issues in generative AI systems beyond simple upper/lower-caste binaries.
