Paper link: https://arxiv.org/pdf/2311.00059
Notion page link: https://kindly-moth-b78.notion.site/5-13-ced5fba646d648f2ba3385764462c21b?pvs=4
Paper review
THE GENERATIVE AI PARADOX:“What It Can Create, It May Not Understand” (ICLR 2024, West et al)
'Paper review' Related Articles
-
When do LLMs need retrieval augmentation? Mitigating LLMs’ overconfidence help retrieval(arXiv, Ni et al)
-
REACT: SYNERGIZING REASONING AND ACTING IN LANGUAGE MODELS(ICLR 2023, Yao et al)
-
Adapting Language Models to Compress Contexts (Chevalier et al. EMNLP 2023)
-
QLoRA: Efficient Finetuning of Quantized LLMs
