Zobrazeno 1 - 10
of 195
pro vyhledávání: '"Mao Xian-Ling"'
Autor:
Lan, Tian, Zhang, Wenwei, Lyu, Chengqi, Li, Shuaibin, Xu, Chen, Huang, Heyan, Lin, Dahua, Mao, Xian-Ling, Chen, Kai
Critique ability, a meta-cognitive capability of humans, presents significant challenges for LLMs to improve. Recent works primarily rely on supervised fine-tuning (SFT) using critiques generated by a single LLM like GPT-4. However, these model-gener
Externí odkaz:
http://arxiv.org/abs/2410.15287
Event extraction has gained extensive research attention due to its broad range of applications. However, the current mainstream evaluation method for event extraction relies on token-level exact match, which misjudges numerous semantic-level correct
Externí odkaz:
http://arxiv.org/abs/2410.09418
It is crucial to utilize events to understand a specific domain. There are lots of research on event extraction in many domains such as news, finance and biology domain. However, scientific domain still lacks event extraction research, including comp
Externí odkaz:
http://arxiv.org/abs/2406.14075
The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to its powerful
Externí odkaz:
http://arxiv.org/abs/2406.02002
Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holist
Externí odkaz:
http://arxiv.org/abs/2403.17636
Autor:
Zhuo, Le, Chi, Zewen, Xu, Minghao, Huang, Heyan, Zheng, Heqi, He, Conghui, Mao, Xian-Ling, Zhang, Wentao
We propose ProtLLM, a versatile cross-modal large language model (LLM) for both protein-centric and protein-language tasks. ProtLLM features a unique dynamic protein mounting mechanism, enabling it to handle complex inputs where the natural language
Externí odkaz:
http://arxiv.org/abs/2403.07920
Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to evaluate cri
Externí odkaz:
http://arxiv.org/abs/2402.13764
Autor:
Zhao, Sen, Wei, Wei, Mao, Xian-Ling, Zhu, Shuai, Yang, Minghui, Wen, Zujie, Chen, Dangyang, Zhu, Feida
Conversational recommendation systems (CRS) aim to interactively acquire user preferences and accordingly recommend items to users. Accurately learning the dynamic user preferences is of crucial importance for CRS. Previous works learn the user prefe
Externí odkaz:
http://arxiv.org/abs/2307.14024
Conversational recommender systems (CRS) aim to timely trace the dynamic interests of users through dialogues and generate relevant responses for item recommendations. Recently, various external knowledge bases (especially knowledge graphs) are incor
Externí odkaz:
http://arxiv.org/abs/2307.10543
Publikováno v:
The Eleventh International Conference on Learning Representations (ICLR 2023)
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying text segments (e.g., words or phrases) from an existing text collecti
Externí odkaz:
http://arxiv.org/abs/2307.06962