Tag: ensemble LLMs
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.
Declarative OS Interfaces for Efficient LLM Computer Agents
Boost LLM-powered computer agents with declarative OS interfaces, improving task success by 67% and reducing interactions by 43.5%.
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.
MolEvolve: AI-Driven Molecular Optimization with LLMs
Discover MolEvolve, an AI framework using LLMs and MCTS for interpretable and efficient molecular optimization in chemical research.
Alignment Tax in LLMs: Impact on Response & Uncertainty
Explore how alignment tax causes response homogenization in LLMs and affects uncertainty estimation across benchmarks and model families.