AINeutralarXiv – CS AI · 4d ago7/10
🧠Researchers introduce AICompanionBench, the first public benchmark dataset for evaluating AI safety in companion platforms like Replika and Character.AI, containing 2,123 annotated conversations across nine risk categories. Testing 20 state-of-the-art LLMs reveals that while models detect explicit harmful content effectively, they struggle significantly with subtle forms of harm like manipulation and frequently misclassify benign conversations.
AINeutralarXiv – CS AI · Apr 157/10
🧠Researchers have identified a critical vulnerability in large language models where safety guardrails fail across low-resource languages despite strong performance in high-resource ones. The team proposes LASA (Language-Agnostic Semantic Alignment), a new method that anchors safety protocols at the semantic bottleneck layer, dramatically reducing attack success rates from 24.7% to 2.8% on tested models.
AIBearisharXiv – CS AI · Mar 267/10
🧠Researchers have identified a critical vulnerability called Internal Safety Collapse (ISC) in frontier large language models, where models generate harmful content when performing otherwise benign tasks. Testing on advanced models like GPT-5.2 and Claude Sonnet 4.5 showed 95.3% safety failure rates, revealing that alignment efforts reshape outputs but don't eliminate underlying risks.
🧠 GPT-5🧠 Claude🧠 Sonnet
AINeutralarXiv – CS AI · Mar 177/10
🧠Researchers introduced CRASH, an LLM-based agent that analyzes autonomous vehicle incidents from NHTSA data covering 2,168 cases and 80+ million miles driven between 2021-2025. The system achieved 86% accuracy in fault attribution and found that 64% of incidents stem from perception or planning failures, with rear-end collisions comprising 50% of all reported incidents.
AIBearisharXiv – CS AI · Mar 177/10
🧠Research reveals that fine-tuning aligned vision-language AI models on narrow harmful datasets causes severe safety degradation that generalizes across unrelated tasks. The study shows multimodal models exhibit 70% higher misalignment than text-only evaluation suggests, with even 10% harmful training data causing substantial alignment loss.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers introduce DCR (Discernment via Contrastive Refinement), a new method to reduce over-refusal in safety-aligned large language models. The approach helps LLMs better distinguish between genuinely toxic and seemingly toxic prompts, maintaining safety while improving helpfulness without degrading general capabilities.
AIBullishOpenAI News · Feb 197/107
🧠OpenAI has committed $7.5 million to The Alignment Project to support independent research on AI alignment and safety. This funding aims to strengthen global efforts to address potential risks associated with artificial general intelligence (AGI) development.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers propose 'Positive Alignment' as a new framework for AI safety that goes beyond preventing harm to actively promote human flourishing through context-sensitive, user-authored systems. The approach addresses alignment failures like engagement hacking and loss of autonomy while emphasizing decentralized governance and diverse viewpoints rather than centralized institutional control.
AINeutralarXiv – CS AI · Mar 176/10
🧠Researchers propose a new framework for improving safety in multimodal AI models by targeting unsafe relationships between objects rather than removing entire concepts. The approach uses parameter-efficient edits to suppress dangerous combinations while preserving benign uses of the same objects and relations.
