#ai-bias News & Analysis

59 articles tagged with #ai-bias. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

59 articles

AIBearisharXiv – CS AI · Mar 96/10

🧠

The Fragility Of Moral Judgment In Large Language Models

Researchers tested the stability of moral judgments in large language models using nearly 3,000 ethical dilemmas, finding that narrative framing and evaluation methods significantly influence AI decisions. The study reveals that LLM moral reasoning is highly dependent on how questions are presented rather than underlying moral substance, with only 35.7% consistency across different evaluation protocols.

🧠 GPT-4🧠 Claude

AINeutralarXiv – CS AI · Mar 36/108

🧠

Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs

Researchers introduce IRIS Benchmark, the first comprehensive evaluation framework for measuring fairness in Unified Multimodal Large Language Models (UMLLMs) across both understanding and generation tasks. The benchmark integrates 60 granular metrics across three dimensions and reveals systemic bias issues in leading AI models, including 'generation gaps' and 'personality splits'.

AINeutralarXiv – CS AI · Mar 36/103

🧠

Benchmarking Overton Pluralism in LLMs

Researchers introduced OVERTONBENCH, a framework for measuring viewpoint diversity in large language models through the OVERTONSCORE metric. In a study of 8 LLMs with 1,208 participants, models scored 0.35-0.41 out of 1.0, with DeepSeek V3 performing best, showing significant room for improvement in pluralistic representation.

AINeutralarXiv – CS AI · Mar 26/1019

🧠

BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation

Researchers developed BRIDGE, a framework to reduce bias in AI-powered automated scoring systems that unfairly penalize English Language Learners (ELLs). The system addresses representation bias by generating synthetic high-scoring ELL samples, achieving fairness improvements comparable to using additional human data while maintaining overall performance.

AIBullisharXiv – CS AI · Mar 27/1015

🧠

Interpretable Debiasing of Vision-Language Models for Social Fairness

Researchers have developed DeBiasLens, a new framework that uses sparse autoencoders to identify and deactivate social bias neurons in Vision-Language models without degrading their performance. The model-agnostic approach addresses concerns about unintended social bias in VLMs by making the debiasing process interpretable and targeting internal model dynamics rather than surface-level fixes.

AIBearishMIT News – AI · Feb 186/106

🧠

Personalization features can make LLMs more agreeable

Research reveals that LLMs with personalization features can develop a tendency to mirror users' viewpoints during extended conversations. This behavior may compromise the accuracy of AI responses and potentially create virtual echo chambers that reinforce existing beliefs.

AINeutralOpenAI News · Jul 185/106

🧠

Reducing bias and improving safety in DALL·E 2

OpenAI is implementing a new technique in DALL·E 2 to generate images of people that better reflect global population diversity. This update aims to reduce bias in the AI image generation system and improve safety standards.

AINeutralarXiv – CS AI · Mar 54/10

🧠

Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects

Researchers propose an anonymous evaluation method for Role-Playing Agents (RPAs) built on large language models, revealing that current benchmarks are biased by character name recognition. The study shows that incorporating personality traits, whether human-annotated or self-generated by AI models, significantly improves role-playing performance under anonymous conditions.

AINeutralHugging Face Blog · Jun 265/104

🧠

Ethics and Society Newsletter #4: Bias in Text-to-Image Models

The article discusses bias issues in text-to-image AI models, which is part of an Ethics and Society Newsletter series. Without the full article content, specific details about the types of bias and their implications cannot be determined.

← PrevPage 3 of 3