#model-representations News & Analysis

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

2 articles

AIBullisharXiv – CS AI · Jun 17/10

🧠

Towards Atoms of Large Language Models

Researchers introduce Atom Theory to identify fundamental representational units (FRUs) in large language models, defining ideal atoms through two criteria: faithfulness and stability. Using threshold-activated sparse autoencoders, they successfully identify atoms achieving 99.9% faithfulness and 99.8% stability across multiple LLM architectures, advancing understanding of how LLMs process and represent information.

🧠 Llama

AINeutralarXiv – CS AI · Mar 267/10

🧠

Exploring How Fair Model Representations Relate to Fair Recommendations

Researchers challenge the assumption that fair model representations in recommender systems translate to fair recommendations. Their study reveals that while optimizing for fair representations improves recommendation parity, representation-level evaluation is not a reliable proxy for measuring actual fairness in recommendations when comparing models.

🏢 Meta