Zhepei Wei
@zhepei.bsky.social
CS Ph.D. student @ UVA. ML/NLP/LLM.
https://weizhepei.com
https://weizhepei.com
Reposted by Zhepei Wei
🏃 Zhepei Wei presented "Fast and Accurate Language Model Decoding via Parallel Token Processing"
openreview.net/forum?id=coZ...
@zhepei.bsky.social @wlchen.bsky.social, Xinyu Zhu, Yu Meng
#NeurIPS2024 #AdaptiveFoundationModels
openreview.net/forum?id=coZ...
@zhepei.bsky.social @wlchen.bsky.social, Xinyu Zhu, Yu Meng
#NeurIPS2024 #AdaptiveFoundationModels
December 19, 2024 at 4:59 AM
🏃 Zhepei Wei presented "Fast and Accurate Language Model Decoding via Parallel Token Processing"
openreview.net/forum?id=coZ...
@zhepei.bsky.social @wlchen.bsky.social, Xinyu Zhu, Yu Meng
#NeurIPS2024 #AdaptiveFoundationModels
openreview.net/forum?id=coZ...
@zhepei.bsky.social @wlchen.bsky.social, Xinyu Zhu, Yu Meng
#NeurIPS2024 #AdaptiveFoundationModels
Great list! Thanks for the efforts, Orion! Our recent work enabled LLMs to generate their OWN supervision for denoising retrieved information in RAG, achieving better accuracy and enhanced verifiability. If you’re interested, feel free to check out InstructRAG! paper link: arxiv.org/abs/2406.13629
InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce mislead...
arxiv.org
November 23, 2024 at 9:53 PM
Great list! Thanks for the efforts, Orion! Our recent work enabled LLMs to generate their OWN supervision for denoising retrieved information in RAG, achieving better accuracy and enhanced verifiability. If you’re interested, feel free to check out InstructRAG! paper link: arxiv.org/abs/2406.13629