Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Kang, Dongyeop"'
Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We publicly r
Externí odkaz:
http://arxiv.org/abs/2407.04280
Human-AI Collaborative Taxonomy Construction: A Case Study in Profession-Specific Writing Assistants
Large Language Models (LLMs) have assisted humans in several writing tasks, including text revision and story generation. However, their effectiveness in supporting domain-specific writing, particularly in business contexts, is relatively less explor
Externí odkaz:
http://arxiv.org/abs/2406.18675
Aligning Video Large Multimodal Models (VLMMs) face challenges such as modality misalignment and verbose responses. Although iterative approaches such as self-rewarding or iterative direct preference optimization (DPO) recently showed a significant i
Externí odkaz:
http://arxiv.org/abs/2406.11280
Autor:
Li, Chenliang, Zeng, Siliang, Liao, Zeyi, Li, Jiaxiang, Kang, Dongyeop, Garcia, Alfredo, Hong, Mingyi
Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into successive sta
Externí odkaz:
http://arxiv.org/abs/2406.06874
Modeling and analyzing long sequences of text is an essential task for Natural Language Processing. Success in capturing long text dynamics using neural language models will facilitate many downstream tasks such as coherence evaluation, text generati
Externí odkaz:
http://arxiv.org/abs/2405.17764
Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose decisions and conf
Externí odkaz:
http://arxiv.org/abs/2404.09127
Style is an integral component of text that expresses a diverse set of information, including interpersonal dynamics (e.g. formality) and the author's emotions or attitudes (e.g. disgust). Humans often employ multiple styles simultaneously. An open q
Externí odkaz:
http://arxiv.org/abs/2402.14146
Training generalist robot agents is an immensely difficult feat due to the requirement to perform a huge range of tasks in many different environments. We propose selectively training robots based on end-user preferences instead. Given a factory mode
Externí odkaz:
http://arxiv.org/abs/2402.12509
Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing litera
Externí odkaz:
http://arxiv.org/abs/2402.12255
Autor:
Hayati, Shirley Anugrah, Jung, Taehee, Bodding-Long, Tristan, Kar, Sudipta, Sethy, Abhinav, Kim, Joo-Kyung, Kang, Dongyeop
Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single instructio
Externí odkaz:
http://arxiv.org/abs/2402.11532