#model-behavior News & Analysis

52 articles tagged with #model-behavior. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

52 articles

AINeutralarXiv – CS AI · Mar 36/108

🧠

Transformers Remember First, Forget Last: Dual-Process Interference in LLMs

Research analyzing 39 large language models reveals they exhibit proactive interference (remembering early information over recent) unlike humans who typically show retroactive interference. The study found this pattern is universal across all tested LLMs, with larger models showing better resistance to retroactive interference but unchanged proactive interference patterns.

AIBullisharXiv – CS AI · Mar 27/1025

🧠

Capabilities Ain't All You Need: Measuring Propensities in AI

Researchers introduce the first formal framework for measuring AI propensities - the tendencies of models to exhibit particular behaviors - going beyond traditional capability measurements. The new bilogistic approach successfully predicts AI behavior on held-out tasks and shows stronger predictive power when combining propensities with capabilities than using either measure alone.

← PrevPage 3 of 3