Science ❯ Computer Science ❯ Artificial Intelligence ❯ Machine Learning

Model Evaluation

Anthropic Moves Toward an October IPO as Scrutiny, Safety Tests and State Lobbying Intensify

Investor meetings and a confidential SEC filing point to a possible fall public listing after regulators limited access to the company’s top models.

New Retrieval Methods Outperform One-Size-Fits-All RAG on Multi‑Hop Tasks

Cluster of Papers Push RAG Toward Multi‑Agent, Graph‑Grounded and Federated Designs

Google Releases TranslateGemma, an Open Suite of Efficient Translation Models

Poetic Prompts Defeat AI Safety Across Models, Averaging 62% Success

RAG Advances Spotlight Structured Retrieval Gains and Safety Risks in Agentic RL Search

LLM-Agent Research Coalesces Around Generalizability, RLVR, and Grounded Retrieval

LLM Vulnerabilities Drive Emergence of Self-Improving AI Frameworks