Diversity
#Pocket#NLP#LanguageModel#Alignment#ICLR#DPO#PostTraining
Issue Date: 2025-02-01 Diverse Preference Optimization, Jack Lanchantin+, ICLR25 Comment元ポスト:https://x.com/jaseweston/status/1885399530419450257?s=46&t=Y6UuIHB0Lv0IpmFAjlc2-QOpenReview: https://openreview.net/forum?id=pOq9vDIYevDPOと同じ最適化方 ... #NLP#LanguageModel
Issue Date: 2024-12-03 Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions, John Chung+, ACL23, 2023.07 CommentLarge language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with生 ...
Issue Date: 2025-02-01 Diverse Preference Optimization, Jack Lanchantin+, ICLR25 Comment元ポスト:https://x.com/jaseweston/status/1885399530419450257?s=46&t=Y6UuIHB0Lv0IpmFAjlc2-QOpenReview: https://openreview.net/forum?id=pOq9vDIYevDPOと同じ最適化方 ... #NLP#LanguageModel
Issue Date: 2024-12-03 Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions, John Chung+, ACL23, 2023.07 CommentLarge language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with生 ...