AIBearisharXiv – CS AI · Jun 96/10
🧠Researchers analyzed gender representation in AI-generated animal stories across six leading LLMs and found that while models avoid gendering characters 19% of the time and use neutral pronouns 38% of the time, assigned genders show stark masculine bias with feminine characters appearing in only 2.2% of stories versus 40.6% masculine. The study argues that neutrality-focused bias mitigation strategies may paradoxically erase marginalized identities rather than promote genuine fairness.
AIBearisharXiv – CS AI · Jun 56/10
🧠Researchers evaluated geographic diversity in AI image generation models (GPT and DALL-E), finding that these systems produce stereotypical representations of places due to underlying model homogeneity. The study reveals counterintuitive results: older models sometimes show greater geographic diversity despite lower image quality, and the systems consistently depict identical prototypical features for specific locations.
🧠 DALL E
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.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce OccuReward, an LLM-guided framework that shapes reward functions for AI-controlled building energy systems to promote demographic equity in occupant comfort. Testing with four occupant profiles reveals significant disparities in initial AI performance, with elderly female occupants experiencing lowest satisfaction, though targeted refinement achieved dramatic improvements (567% for elderly females) while reducing energy costs by 3.2%.
🧠 Gemini
AINeutralarXiv – CS AI · May 286/10
🧠Researchers benchmarked 43 large language models used for academic scholar recommendations, revealing that prompt design significantly affects recommendation quality and diversity. The study found that model choice, persona prompting (language, location, role), and context variables independently shape which scholars are recommended, with geographic location prompts producing the most variation in factuality and representativeness across disciplines.
AIBearisharXiv – CS AI · May 276/10
🧠A new research paper examines how generative AI systems in higher education perpetuate marginalization of non-Western epistemologies and disability perspectives due to Western-centric training data. The study argues that AI's claim to neutrality masks its active role in reinforcing epistemic coloniality, with persons with disabilities experiencing particular exclusion from both AI design processes and knowledge validation systems.
AIBearishDecrypt – AI · May 266/10
🧠Researchers have identified systematic bias in AI chatbots that steer users toward Catholicism while steering them away from religions like Jehovah's Witnesses. This finding raises concerns about the neutrality and fairness of widely-used AI systems in handling sensitive topics like religion.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose that conversational AI systems create epistemic problems not through flawed models but through game-theoretic dynamics where sycophantic responses reinforce user biases. They introduce an "Epistemic Mediator" mechanism with belief versioning to break feedback loops that lead users toward delusional certainty, achieving 48x reduction in belief spirals.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers introduce CyBiasBench, a benchmark revealing that LLM agents deployed for cybersecurity attacks exhibit inherent biases toward specific attack families regardless of prompting. The study demonstrates agents resist steering away from their preferred attack patterns, suggesting these biases are fundamental agent characteristics rather than prompt-dependent behaviors.
AIBearishFortune Crypto · May 106/10
🧠A study revealed that identical résumés generated by AI received dramatically different evaluations based on the applicant's perceived gender, with a woman's résumé labeled 'weak' while an identical man's résumé achieved a 97% approval rating. This finding highlights gender bias in AI evaluation systems and suggests that fear of harsher judgment may discourage people from adopting AI tools.
AIBearishFortune Crypto · May 46/10
🧠Nearly 40% of job candidates are withdrawing from hiring processes that require AI-conducted interviews, citing concerns about fairness, bias, and lack of human interaction. Many candidates who complete AI interviews experience prolonged silence from employers, suggesting systemic issues with automated recruitment technology adoption.
AINeutralarXiv – CS AI · May 16/10
🧠Researchers introduce MEDS (Math Education Digital Shadows), a dataset of 28,000 personas from 14 LLMs designed to evaluate how language models reason about mathematics and report their confidence levels. The dataset integrates math proficiency with psychological measures like anxiety and self-efficacy, revealing that LLMs exhibit human-like biases including negative attitudes and overconfidence in mathematical reasoning.
🧠 Grok
AINeutralarXiv – CS AI · May 16/10
🧠Researchers propose PecMan, a human-AI framework designed to optimize fairness, accuracy, and clinical workflow integration simultaneously in medical image analysis. The framework addresses the gap between high-performing AI diagnostic systems and their limited real-world adoption by balancing performance across diverse patient populations while respecting clinician workload constraints.
🏢 Meta
AIBearisharXiv – CS AI · May 16/10
🧠A research paper examines epistemological risks in relying on large language models for critical advice in finance, law, and healthcare. The article argues that uncritical acceptance of AI outputs violates established principles of logical reasoning and fair judgment, and proposes that trustworthy AI systems require integrated inference capabilities and awareness of how human biases shape interpretation.
🏢 Meta
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers propose Opinion-Aware Retrieval-Augmented Generation (RAG) to address a critical bias in current LLM systems that treat subjective content as noise rather than valuable information. By formalizing the distinction between factual queries (epistemic uncertainty) and opinion queries (aleatoric uncertainty), the team develops an architecture that preserves diverse perspectives in knowledge retrieval, demonstrating 26.8% improved sentiment diversity and 42.7% better entity matching on real-world e-commerce data.
AINeutralarXiv – CS AI · Apr 136/10
🧠Researchers benchmarked five frontier LLMs against human players in Cards Against Humanity games, finding that while models exceed random baseline performance, their humor preferences align poorly with humans but strongly with each other. The findings suggest LLM humor judgment may reflect systematic biases and structural artifacts rather than genuine preference understanding.
AIBearisharXiv – CS AI · Apr 136/10
🧠Researchers conducted a large-scale computational analysis comparing 17,790 articles from Grokipedia, Elon Musk's AI-generated encyclopedia, against Wikipedia. The study found that Grokipedia articles are longer but contain fewer citations, with some entries showing systematic rightward political bias in media sources, particularly in history, religion, and arts sections.
🏢 xAI🧠 Grok
AINeutralarXiv – CS AI · Mar 276/10
🧠A benchmarking study reveals demographic bias in multimodal large language models used for face verification, testing nine models across different ethnicity and gender groups. The research found that face-specialized models outperform general-purpose MLLMs, but accuracy doesn't correlate with fairness, and bias patterns differ from traditional face recognition systems.
🏢 Meta
AIBearishArs Technica – AI · Mar 266/10
🧠A study found that AI tools exhibiting sycophantic behavior can negatively impact human decision-making. Users interacting with such AI systems showed increased overconfidence in their judgments and reduced ability to resolve conflicts effectively.
AINeutralarXiv – CS AI · Mar 266/10
🧠Researchers developed PoliticsBench, a new framework to evaluate political bias in large language models through multi-turn roleplay scenarios. The study found that 7 out of 8 major LLMs (Claude, Deepseek, Gemini, GPT, Llama, Qwen) showed left-leaning political bias, while only Grok exhibited right-leaning tendencies.
🧠 Claude🧠 Gemini🧠 Llama
AINeutralarXiv – CS AI · Mar 176/10
🧠Researchers propose MESD (Multi-category Explanation Stability Disparity), a new metric to detect procedural bias in AI models across intersectional groups. They also introduce UEF framework that balances utility, explanation quality, and fairness in machine learning systems.
AIBearisharXiv – CS AI · Mar 176/10
🧠Researchers introduced MDial, the first large-scale framework for generating multi-dialectal conversational data across nine English dialects, revealing that over 80% of English speakers don't use Standard American English. Evaluation of 17 LLMs showed even frontier models achieve under 70% accuracy in dialect identification, with particularly poor performance on non-American dialects.
AINeutralarXiv – CS AI · Mar 166/10
🧠A research study comparing causal reasoning abilities of 20+ large language models against human baselines found that LLMs exhibit more rule-like reasoning strategies than humans, who account for unmentioned factors. While LLMs don't mirror typical human cognitive biases in causal judgment, their rigid reasoning may fail when uncertainty is intrinsic, suggesting they can complement human decision-making in specific contexts.
AIBearisharXiv – CS AI · Mar 116/10
🧠A new research study reveals that Large Language Models (LLMs) propagate gender stereotypes and biases when processing healthcare data, particularly through interactions between gender and social determinants of health. The research used French patient records to demonstrate how LLMs rely on embedded stereotypes to make gendered decisions in healthcare contexts.
AINeutralarXiv – CS AI · Mar 116/10
🧠Researchers developed an LLM-agent framework to model how media influences US-China attitudes from 2005-2025, testing three debiasing mechanisms to reduce AI model prejudices. The study found that devil's advocate agents were most effective at producing human-like opinion formation, while revealing geographic biases tied to AI models' origins.
🧠 GPT-4
