論文標題:Reflexion: Language Agents with Verbal Reinforcement Learning論文鏈接:https://arxiv.or...
論文標題:Reflexion: Language Agents with Verbal Reinforcement Learning論文鏈接:https://arxiv.or...
論文標題:Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference O...
論文標題:Direct Preference Optimization: Your Language Model is Secretly a Reward Model論文鏈接...
一、概述 大語言模型(LLMs)在預訓練的過程中通常會捕捉數(shù)據(jù)的特征,而這些訓練數(shù)據(jù)通常既包含高質量的也包含低質量的,因此模型有時會產(chǎn)生不被期望的行為,如編造事實,生成有偏見...
論文標題:LoRA: Low-Rank Adaptation of Large Language Models論文鏈接:https://arxiv.org/abs/2106....
論文標題:Chain-of-Thought Prompting Elicits Reasoning in Large Language Models論文鏈接:https://...
論文標題:Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallel...
論文標題:Tree of Thoughts: Deliberate Problem Solving with Large Language Models論文鏈接:https:...
論文標題:LIMA: Less Is More for Alignment論文鏈接:https://arxiv.org/abs/2305.11206[https://arxi...