MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification
"LLM性能" 相关文章
GneissWeb: Preparing High Quality Data for LLMs at Scale
LLM-Crowdsourced: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy
Princeton University Researchers Introduce Self-MoA and Self-MoA-Seq: Optimizing LLM Performance with Single-Model Ensembles
KAG开源了，知识增强掀翻RAG，性能翻倍
Where do LLMs spend their FLOPS?
Archon: A Machine Learning Framework for Large Language Model Enhancement Using Automated Inference-Time Architecture Search for Improved Task Performance
MAGICORE: An AI Framework for Multi Agent Iteration for Coarse-to-fine Refinement
CoT神话破灭，并非LLM标配！三大学府机构联手证实，CoT仅在数学符号推理有用
