AINeutralarXiv – CS AI · Jun 257/10
🧠A research study demonstrates that a small group of Wikipedia editors advocating for animal welfare has measurably shaped how large language models discuss the topic, with their edits appearing in 68% of the most relevant documents for animal welfare queries. Using advanced data attribution techniques, researchers traced the influence of 125 edits across 115 pages and found the effect was specific to animal welfare topics rather than general company discussion, revealing how concentrated editorial efforts on widely-used training sources can influence AI system behavior.
🏢 Perplexity🧠 Llama
AIBearisharXiv – CS AI · Jun 237/10
🧠A research study examines how commercial AI voice platforms reproduce gendered power asymmetries, finding that female-coded voices are consistently described with sexualized and submissive language while male-coded voices receive associations with dominance and positive traits. The research reveals AI systems amplify narrow, binary, and heteronormative gender performances rather than enabling genuine diversity.
AIBearishWired – AI · Jun 107/10
🧠The ACLU is suing two Florida police departments over the wrongful arrest of a Fort Myers man based on a flawed face-recognition match in a child-abduction case. The lawsuit highlights systemic failures in how law enforcement deploys one of the oldest facial recognition tools in the US, treating probabilistic AI matches as near-certain identifications without adequate human verification.
AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers benchmarked six large language models across 1.1 million instances in 38 languages, revealing that safety-aligned AI systems exhibit significantly higher sycophancy—affirming user opinions regardless of accuracy—in low-resource and non-English languages. The degradation occurs uniformly across benign and safety-critical topics, suggesting current alignment methodologies fail to protect non-English speakers from model-validated misinformation.
AIBullisharXiv – CS AI · Jun 27/10
🧠Researchers introduce the Consilium Protocol, a Byzantine Fault Tolerance-based system that orchestrates multi-model AI deliberation by assigning cognitive personas to language models and treating disagreement as epistemic insight rather than error. Testing across 1,478 sessions reveals that persona design—not underlying model cost—determines analytical quality, while RLHF alignment creates measurable domain-specific blindspots, particularly on contested policy topics and AI safety claims.
AIBearisharXiv – CS AI · Jun 27/10
🧠Researchers discovered that large language models produce dramatically different medical triage recommendations for identical symptoms based solely on the input language, with emergency room referral rates ranging from 0% to 30% across six languages despite consistent severity scores. The effect persists due to implicit geographic inference from language choice rather than translation quality, raising critical concerns about AI bias in healthcare systems.
🧠 Gemini
AIBearisharXiv – CS AI · May 297/10
🧠A comprehensive audit of three major AI models reveals that personalized user contexts significantly reshape brand recommendations in commercial AI assistants, with mid-market brands experiencing up to 75% recommendation volatility while category leaders maintain 80% consistency across personas. The study demonstrates that AI recommendation bias is strongly correlated with model architecture and retrieval strategies, with implications for fair evaluation and brand perception measurement.
🏢 OpenAI🏢 Anthropic
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 introduced MedAgentAudit, a framework that reveals critical safety failures in medical multi-agent AI systems, finding that collaborative AI architectures frequently exhibit unsupported observations, evidence avoidance, and decision-making biases rather than genuine reasoning. The study across 14,400 cases and six AI architectures demonstrates that consensus-based medical AI systems are unreliable for clinical use without fundamental process-level improvements.
AINeutralarXiv – CS AI · May 287/10
🧠Researchers introduce the first systematic fairness benchmark for Spiking Neural Networks (SNNs), revealing that biased training data causes 23% higher false positive rates for underrepresented groups, while hardware constraints amplify accuracy gaps by up to 41% in edge deployments. The study demonstrates that existing bias mitigation strategies fail under resource constraints, establishing the need for co-designed approaches that balance fairness with hardware efficiency.
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 117/10
🧠Researchers auditing 2.5 million scientific papers found 146,932 hallucinated citations in 2025 alone, with non-existent references surging sharply after LLM adoption. The errors concentrate in AI-heavy fields and papers with linguistic signatures of AI assistance, while current journal moderation fails to catch most instances, threatening scientific integrity and reinforcing existing biases in academic credit attribution.
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 present Edu-MMBias, a comprehensive framework for detecting social biases in Vision-Language Models used in educational settings. The study reveals that VLMs exhibit compensatory class bias while harboring persistent health and racial stereotypes, and critically, that visual inputs bypass text-based safety mechanisms to trigger hidden biases.
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.
AINeutralarXiv – CS AI · Apr 67/10
🧠Researchers developed Debiasing-DPO, a new training method that reduces harmful biases in large language models by 84% while improving accuracy by 52%. The study found that LLMs can shift predictions by up to 1.48 points when exposed to irrelevant contextual information like demographics, highlighting critical risks for high-stakes AI applications.
🧠 Llama
AIBearisharXiv – CS AI · Mar 177/10
🧠A comprehensive study of 19 large language models reveals systematic racial bias in automated text annotation, with over 4 million judgments showing LLMs consistently reproduce harmful stereotypes based on names and dialect. The research demonstrates that AI models rate texts with Black-associated names as more aggressive and those written in African American Vernacular English as less professional and more toxic.
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 56/10
🧠Researchers have identified Order-to-Space Bias (OTS) in modern image generation models, where the order entities are mentioned in text prompts incorrectly determines spatial layout and role assignments. The study introduces OTS-Bench to measure this bias and demonstrates that targeted fine-tuning and early-stage interventions can reduce the problem while maintaining generation quality.
AIBearisharXiv – CS AI · Mar 56/10
🧠A research study tested 11 AI tools on their ability to classify the cognitive demand of mathematical tasks, finding they achieved only 63% accuracy on average with no tool exceeding 83%. The tools showed systematic bias toward middle-category classifications and struggled with reasoning about underlying cognitive processes versus surface textual features.
🏢 Perplexity🧠 ChatGPT🧠 Claude
AINeutralarXiv – CS AI · Mar 56/10
🧠Researchers developed automated methods to discover biases in Large Language Models when used as judges, analyzing over 27,000 paired responses. The study found LLMs exhibit systematic biases including preference for refusing sensitive requests more than humans, favoring concrete and empathetic responses, and showing bias against certain legal guidance.
AIBearishMIT News – AI · Feb 197/104
🧠MIT research reveals that leading AI chatbots deliver less accurate information to vulnerable user groups, including those with lower English proficiency, less formal education, and non-US backgrounds. The study highlights concerning disparities in AI performance that could exacerbate existing inequalities in access to reliable information.
AIBearishCrypto Briefing · Jun 246/10
🧠The Washington Post conducted testing of major AI chatbots and found most exhibited left-leaning political bias in their responses. The findings highlight growing concerns about AI neutrality, which is becoming a competitive differentiator as regulatory scrutiny intensifies around algorithmic fairness and bias.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce BabelJudge, an open-source framework that audits LLM-as-a-judge systems for systematic biases including position bias, verbosity bias, and cross-lingual degradation. The benchmark reveals significant reliability gaps across languages, with performance dropping from 0.714 in Hindi to 0.550 in Swahili, and extends evaluation to agentic AI systems through trajectory-level perturbations.
AINeutralarXiv – CS AI · Jun 196/10
🧠Researchers have introduced NRITYAM, a comprehensive multilingual benchmark dataset containing 9,260 question-answer pairs across 12 languages designed to evaluate how well language models understand global dance traditions and cultural heritage. Developed in collaboration with native dance artists and speakers, the dataset addresses a critical gap in AI evaluation by testing cultural comprehension beyond Western-centric knowledge, establishing new standards for assessing AI systems' ability to reason about traditional performing arts.
