#distribution-shifts News & Analysis

3 articles tagged with #distribution-shifts. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AIBearisharXiv – CS AI · Mar 277/10

🧠

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts

Researchers have identified a new vulnerability in large language models called 'natural distribution shifts' where seemingly benign prompts can bypass safety mechanisms to reveal harmful content. They developed ActorBreaker, a novel attack method that uses multi-turn prompts to gradually expose unsafe content, and proposed expanding safety training to address this vulnerability.

AINeutralarXiv – CS AI · Mar 266/10

🧠

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

Researchers investigated whether Vision-Language Models (VLMs) can reason robustly under distribution shifts and found that fine-tuned VLMs achieve high accuracy in-distribution but fail to generalize. They propose VLC, a neuro-symbolic method combining VLM-based concept recognition with circuit-based symbolic reasoning that demonstrates consistent performance under covariate shifts.

AINeutralarXiv – CS AI · Mar 27/1012

🧠

Planning under Distribution Shifts with Causal POMDPs

Researchers propose a new theoretical framework for AI planning under changing conditions using causal POMDPs (Partially Observable Markov Decision Processes). The framework represents environmental changes as interventions, enabling AI systems to evaluate and adapt plans when underlying conditions shift while maintaining computational tractability.