Zobrazeno 1 - 10
of 528
pro vyhledávání: '"Zhou Yujia"'
Autor:
Ye, Ziyi, Li, Xiangsheng, Li, Qiuchi, Ai, Qingyao, Zhou, Yujia, Shen, Wei, Yan, Dong, Liu, Yiqun
Learning from preference feedback is a common practice for aligning large language models~(LLMs) with human value. Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to produce a s
Externí odkaz:
http://arxiv.org/abs/2410.03742
Autor:
Zhou, Yujia, Liu, Yan, Li, Xiaoxi, Jin, Jiajie, Qian, Hongjin, Liu, Zheng, Li, Chaozhuo, Dou, Zhicheng, Ho, Tsung-Yi, Yu, Philip S.
Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). While much of the current research in this field focuses on performance optimization, particularly in terms of accuracy
Externí odkaz:
http://arxiv.org/abs/2409.10102
The learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we argue that the long-LLMs are not a necessity to solve long-context tasks, as common long-context tasks are short-context solvable, i.e.
Externí odkaz:
http://arxiv.org/abs/2405.15318
Autor:
Li, Xiaoxi, Jin, Jiajie, Zhou, Yujia, Zhang, Yuyao, Zhang, Peitian, Zhu, Yutao, Dou, Zhicheng
Information Retrieval (IR) systems are crucial tools for users to access information, widely applied in scenarios like search engines, question answering, and recommendation systems. Traditional IR methods, based on similarity matching to return rank
Externí odkaz:
http://arxiv.org/abs/2404.14851
Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research into dete
Externí odkaz:
http://arxiv.org/abs/2403.06448
Retrieval-augmented large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, addressing inherent challenges in knowledge update and factual inadequacy. However, inconsistencies between retrieval kno
Externí odkaz:
http://arxiv.org/abs/2402.12174
Retrieval-augmented generation have become central in natural language processing due to their efficacy in generating factual content. While traditional methods employ single-time retrieval, more recent approaches have shifted towards multi-time retr
Externí odkaz:
http://arxiv.org/abs/2402.11626
Traditional search engines usually provide identical search results for all users, overlooking individual preferences. To counter this limitation, personalized search has been developed to re-rank results based on user preferences derived from query
Externí odkaz:
http://arxiv.org/abs/2402.10548
This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses using precise evidence text due to
Externí odkaz:
http://arxiv.org/abs/2402.09760
Large language models (LLMs) have gained significant attention in various fields but prone to hallucination, especially in knowledge-intensive (KI) tasks. To address this, retrieval-augmented generation (RAG) has emerged as a popular solution to enha
Externí odkaz:
http://arxiv.org/abs/2402.01176