Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Lee, Kyungjae"'
Distributional reinforcement learning improves performance by effectively capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive. In this paper, we present a regret analysis for distr
Externí odkaz:
http://arxiv.org/abs/2407.21260
Autor:
Kim, Takyoung, Lee, Kyungjae, Jang, Young Rok, Cho, Ji Yong, Kim, Gangwoo, Cho, Minseok, Lee, Moontae
Interactions with billion-scale large language models typically yield long-form responses due to their extensive parametric capacities, along with retrieval-augmented features. While detailed responses provide insightful viewpoint of a specific subje
Externí odkaz:
http://arxiv.org/abs/2407.01158
Autor:
Kim, Seungone, Suk, Juyoung, Cho, Ji Yong, Longpre, Shayne, Kim, Chaeeun, Yoon, Dongkeun, Son, Guijin, Cho, Yejin, Shafayat, Sheikh, Baek, Jinheon, Park, Sue Hyun, Hwang, Hyeonbin, Jo, Jinkyung, Cho, Hyowon, Shin, Haebin, Lee, Seongyun, Oh, Hanseok, Lee, Noah, Ho, Namgyu, Joo, Se June, Ko, Miyoung, Lee, Yoonjoo, Chae, Hyungjoo, Shin, Jamin, Jang, Joel, Ye, Seonghyeon, Lin, Bill Yuchen, Welleck, Sean, Neubig, Graham, Lee, Moontae, Lee, Kyungjae, Seo, Minjoon
As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria like helpfulness and harml
Externí odkaz:
http://arxiv.org/abs/2406.05761
Autor:
Lee, Kyungjae
Thesis advisor: Michael Grubb
This paper investigates the discount rates applied by NFL teams to future draft picks when engaging in trades during the annual NFL Draft. Utilizing a dataset of 353 draft pick trades from 2010 to 2024, the study em
This paper investigates the discount rates applied by NFL teams to future draft picks when engaging in trades during the annual NFL Draft. Utilizing a dataset of 353 draft pick trades from 2010 to 2024, the study em
Externí odkaz:
http://hdl.handle.net/2345/bc-ir:110011
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints. However, the nonlinearity of risk measures makes it cha
Externí odkaz:
http://arxiv.org/abs/2405.18698
Autor:
Kim, Hajung, Kim, Chanhwi, Lee, Hoonick, Jang, Kyochul, Lee, Jiwoo, Lee, Kyungjae, Kim, Gangwoo, Kang, Jaewoo
Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this process is detecting and rejecting unanswerable questions that request infor
Externí odkaz:
http://arxiv.org/abs/2406.00014
Autor:
Kim, Seungone, Suk, Juyoung, Longpre, Shayne, Lin, Bill Yuchen, Shin, Jamin, Welleck, Sean, Neubig, Graham, Lee, Moontae, Lee, Kyungjae, Seo, Minjoon
Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs. However, concerns including transparency, controllability, and affordability strongly motivate the development of open-source LMs specialized in eva
Externí odkaz:
http://arxiv.org/abs/2405.01535
Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions to align t
Externí odkaz:
http://arxiv.org/abs/2403.14238
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 201-215 (2019)
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classif
Externí odkaz:
https://doaj.org/article/24d209e3a74849099e4338e9750dd81b
Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the estimated variance for optimistic exploration may cause biased data coll
Externí odkaz:
http://arxiv.org/abs/2310.16546