Tag: AI language models
Browse our exclusive articles!
Boost LLMs with 4 Tokens: Synergistic Test-time Adaptation
Enhance large language models with SyTTA using only 4 extra tokens for real-time domain adaptation without labeled data or retraining.
Boosting Jailbreak Attacks on LLMs Using Persona Prompts
Explore how persona prompts enhance jailbreak attacks on LLMs, revealing vulnerabilities and impacting AI safety with new genetic algorithm methods.
AI vs Human Responses in Online Mental Health Support
Explore the linguistic differences between AI and human replies in online mental health communities and their impact on support quality.
LLMs vs Chimpanzees: Perspective Taking & Knowledge Skills
Explore how large language models compare to chimpanzees in perspective taking and knowledge state estimation, revealing key AI cognitive gaps.
Graph-Based Evaluation for Domain-Specific LLMs
Discover a graph-based evaluation harness that ensures comprehensive, contamination-resistant testing of domain-specific LLMs using clinical guidelines.