y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#semantic-discrimination News & Analysis

1 article tagged with #semantic-discrimination. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AINeutralarXiv – CS AI · 18h ago6/10
🧠

Phantom transitions in language model fine-tuning

Researchers discovered that language models fail silently when fine-tuned on contexts with near-synonym competitors, exhibiting apparent phase transitions that are actually artifacts of the softmax readout rather than genuine geometric changes. The study identifies two failure modes and demonstrates that apparent discontinuities persist even under LoRA fine-tuning where embedding matrices remain frozen, revealing the phenomenon occurs entirely in the output layer.