Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Chen, Yanda"'
Autor:
Morrill, Todd, Deng, Zhaoyuan, Chen, Yanda, Ananthram, Amith, Leach, Colin Wayne, McKeown, Kathleen
There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm-Agreeable, Arrogant-Calculating) of conversation participants and can
Externí odkaz:
http://arxiv.org/abs/2403.04770
Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there is a star
Externí odkaz:
http://arxiv.org/abs/2402.12530
Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may generate the explanation "all birds can fly" when
Externí odkaz:
http://arxiv.org/abs/2401.13986
Autor:
Chen, Yanda, Zhong, Ruiqi, Ri, Narutatsu, Zhao, Chen, He, He, Steinhardt, Jacob, Yu, Zhou, McKeown, Kathleen
Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs process different inputs? To answer these questions, we propose to evalua
Externí odkaz:
http://arxiv.org/abs/2307.08678
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context lear
Externí odkaz:
http://arxiv.org/abs/2212.10670
In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios. We study the sensitivity of ICL with respect to multiple perturbation types. First, we find that label bias obscures the true sensitiv
Externí odkaz:
http://arxiv.org/abs/2209.07661
The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. To tackle this problem in NLP, we propose $\textit{in-context tuning}$, which recasts adaptation and prediction as a simple sequence prediction problem: to
Externí odkaz:
http://arxiv.org/abs/2110.07814
Autor:
Chen, Yanda, Kedzie, Chris, Nair, Suraj, Galuščáková, Petra, Zhang, Rui, Oard, Douglas W., McKeown, Kathleen
This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based query relevan
Externí odkaz:
http://arxiv.org/abs/2106.02293
Publikováno v:
In Computer Methods in Applied Mechanics and Engineering 15 March 2024 422
Automatically generated synthetic training examples have been shown to improve performance in machine reading comprehension (MRC). Compared to human annotated gold standard data, synthetic training data has unique properties, such as high availabilit
Externí odkaz:
http://arxiv.org/abs/2010.12776