2 articles tagged with #model-internals. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers demonstrate that AI model logits and other accessible model outputs leak significant task-irrelevant information from vision-language models, creating potential security risks through unintentional or malicious information exposure despite apparent safeguards.
Researchers demonstrate that looped transformers like Ouro-2.6B encode human preferences relationally rather than independently, with pairwise evaluators achieving 95.2% accuracy compared to 21.75% for independent classification. The study reveals that preference encoding is fundamentally relational, functioning as an internal consistency probe rather than a direct predictor of human annotations.
