Tag: AI language models
Browse our exclusive articles!
Enhance LLMs Structural Attention with Slash Method
Discover Slash, a training-free method to boost structural attention in LLMs, improving graph reasoning without costly fine-tuning or complex adapters.
Absurd World: Benchmarking LLM Logical Reasoning Skills
Discover Absurd World, a novel framework to test and improve large language models' logical reasoning with absurd yet coherent scenarios.
Do Linear Probes Generalize Better Using Persona Coordinates?
Explore how linear probes with persona coordinates improve generalization in detecting harmful behaviors in language models across datasets.
How Attention Heads Influence Persuasion in LLMs
Discover how a few attention heads reroute large language models, revealing key mechanisms behind LLM persuasion and AI safety.
Emergent Semantic Role Understanding in Language Models
Explore how language models develop semantic role understanding during pre-training and fine-tuning for improved NLP performance.