#linear-probing News & Analysis

2 articles tagged with #linear-probing. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AINeutralarXiv – CS AI · Jun 196/10

🧠

From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models

Researchers systematically analyzed how eight large language models encode essay quality information in their hidden representations across three datasets. Using linear probing and neuron-level analysis, they found that essay quality is encoded in linearly accessible form, emerges progressively across layers, and partially transfers across different essay prompts, with individual 'essay scoring neurons' showing strong correlation to scores.

AINeutralarXiv – CS AI · Jun 116/10

🧠

When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis

Researchers introduce 'fragility' as a complementary metric to linear probing for analyzing large language model pre-training, addressing the limitation that probe accuracy saturates early in training and becomes insensitive to ongoing representational changes. By measuring activation noise tolerance levels, fragility reveals structural evolution in how models encode lexical versus compositional information across layers, demonstrating that data curation and architectural choices leave distinct signatures invisible to traditional accuracy metrics.