Tag: AI language models
Browse our exclusive articles!
WildToolBench: Real-World Benchmark for LLM Tool Use
Discover WildToolBench, a new benchmark revealing the real-world challenges LLMs face in tool use with complex user interactions and low accuracy rates.
SELFDOUBT: Efficient Uncertainty Quantification for Reasoning LLMs
Discover SELFDOUBT, a novel method using the Hedge-to-Verify Ratio to quantify uncertainty in reasoning LLMs with high accuracy and low cost.
Language Models’ Blind Refusal to Break Unjust Rules
Study reveals language models often refuse to bypass unjust or absurd rules, highlighting limits in AI moral reasoning and safety protocols.
Knowledge-Weighted Fine-Tuning to Improve AI Uncertainty
Enhance AI reliability with knowledge-weighted fine-tuning that teaches models when to say 'I don't know' and reduces hallucinations.
Turbulence-like 5/3 Scaling in Contextual Language Models
Discover turbulence-like 5/3 spectral scaling in contextual language embeddings, revealing complex system patterns in human and AI-generated text.