Zobrazeno 1 - 10
of 138
pro vyhledávání: '"Kim, Jaehyung"'
An open challenge in recent machine learning is about how to improve the reasoning capability of large language models (LLMs) in a black-box setting, i.e., without access to detailed information such as output token probabilities. Existing approaches
Externí odkaz:
http://arxiv.org/abs/2406.18695
Autor:
Kim, Jaehyung, Yang, Yiming
As the diversity of users increases, the capability of providing personalized responses by large language models (LLMs) has become increasingly important. Existing approaches have only limited successes in LLM personalization, due to the absence of p
Externí odkaz:
http://arxiv.org/abs/2406.18678
Learning effective representations from raw data is crucial for the success of deep learning methods. However, in the tabular domain, practitioners often prefer augmenting raw column features over using learned representations, as conventional tree-b
Externí odkaz:
http://arxiv.org/abs/2406.08527
Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we propose a ne
Externí odkaz:
http://arxiv.org/abs/2406.04412
Autor:
Kim, Jaehyung, Nam, Jaehyun, Mo, Sangwoo, Park, Jongjin, Lee, Sang-Woo, Seo, Minjoon, Ha, Jung-Woo, Shin, Jinwoo
Large language models (LLMs) have made significant advancements in various natural language processing tasks, including question answering (QA) tasks. While incorporating new information with the retrieval of relevant passages is a promising way to i
Externí odkaz:
http://arxiv.org/abs/2404.13081
Autor:
Song, Woomin, Oh, Seunghyuk, Mo, Sangwoo, Kim, Jaehyung, Yun, Sukmin, Ha, Jung-Woo, Shin, Jinwoo
Large language models (LLMs) have shown remarkable performance in various natural language processing tasks. However, a primary constraint they face is the context limit, i.e., the maximum number of tokens they can process. Previous works have explor
Externí odkaz:
http://arxiv.org/abs/2404.10308
The usage of 3D vision algorithms, such as shape reconstruction, remains limited because they require inputs to be at a fixed canonical rotation. Recently, a simple equivariant network, Vector Neuron (VN) has been proposed that can be easily used wit
Externí odkaz:
http://arxiv.org/abs/2405.04537
Autor:
Tack, Jihoon, Kim, Jaehyung, Mitchell, Eric, Shin, Jinwoo, Teh, Yee Whye, Schwarz, Jonathan Richard
Due to the rapid generation and dissemination of information, large language models (LLMs) quickly run out of date despite enormous development costs. Due to this crucial need to keep models updated, online learning has emerged as a critical necessit
Externí odkaz:
http://arxiv.org/abs/2403.04317
Instruction tuning benefits from large and diverse datasets, however creating such datasets involves a high cost of human labeling. While synthetic datasets generated by large language models (LLMs) have partly solved this issue, they often contain l
Externí odkaz:
http://arxiv.org/abs/2401.16553
Autor:
Das, Debarati, De Langis, Karin, Martin-Boyle, Anna, Kim, Jaehyung, Lee, Minhwa, Kim, Zae Myung, Hayati, Shirley Anugrah, Owan, Risako, Hu, Bin, Parkar, Ritik, Koo, Ryan, Park, Jonginn, Tyagi, Aahan, Ferland, Libby, Roy, Sanjali, Liu, Vincent, Kang, Dongyeop
This work delves into the expanding role of large language models (LLMs) in generating artificial data. LLMs are increasingly employed to create a variety of outputs, including annotations, preferences, instruction prompts, simulated dialogues, and f
Externí odkaz:
http://arxiv.org/abs/2401.14698