Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Sun, Chenkai"'
Autor:
Sun, Chenkai, Yang, Ke, Reddy, Revanth Gangi, Fung, Yi R., Chan, Hou Pong, Small, Kevin, Zhai, ChengXiang, Ji, Heng
The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and preferences. Retrieval augmentation emerges as an effective strategy, as
Externí odkaz:
http://arxiv.org/abs/2402.11060
Pretrained large language models have revolutionized many applications but still face challenges related to cultural bias and a lack of cultural commonsense knowledge crucial for guiding cross-culture communication and interactions. Recognizing the s
Externí odkaz:
http://arxiv.org/abs/2402.09369
Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any acceptance by the
Externí odkaz:
http://arxiv.org/abs/2312.11462
Autor:
Sun, Chenkai, Li, Jinning, Fung, Yi R., Chan, Hou Pong, Abdelzaher, Tarek, Zhai, ChengXiang, Ji, Heng
Automatic response forecasting for news media plays a crucial role in enabling content producers to efficiently predict the impact of news releases and prevent unexpected negative outcomes such as social conflict and moral injury. To effectively fore
Externí odkaz:
http://arxiv.org/abs/2310.13297
Predicting how a user responds to news events enables important applications such as allowing intelligent agents or content producers to estimate the effect on different communities and revise unreleased messages to prevent unexpected bad outcomes su
Externí odkaz:
http://arxiv.org/abs/2305.16470
Autor:
Han, Chi, Xu, Jialiang, Li, Manling, Fung, Yi, Sun, Chenkai, Jiang, Nan, Abdelzaher, Tarek, Ji, Heng
Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain underexplored
Externí odkaz:
http://arxiv.org/abs/2305.12798
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferenc
Externí odkaz:
http://arxiv.org/abs/2209.00068
Autor:
Sun, Chenkai, Li, Weijiang, Xiao, Jinfeng, Parulian, Nikolaus Nova, Zhai, ChengXiang, Ji, Heng
Automated knowledge discovery from trending chemical literature is essential for more efficient biomedical research. How to extract detailed knowledge about chemical reactions from the core chemistry literature is a new emerging challenge that has no
Externí odkaz:
http://arxiv.org/abs/2108.12899
Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various info
Externí odkaz:
http://arxiv.org/abs/2106.15838
Autor:
Zhang, Shimin, Xue, Zhongyuan, He, Zhilong, Wei, Qingyun, Yang, Nana, Wu, Xueyun, Chen, Chun Chao, Sun, Chenkai, Zhong, Hongliang
Publikováno v:
In Chemical Engineering Journal 1 February 2024 481