Zobrazeno 1 - 10
of 1 617
pro vyhledávání: '", Kanishk"'
Autor:
Havrilla, Alex, Dai, Andrew, O'Mahony, Laura, Oostermeijer, Koen, Zisler, Vera, Albalak, Alon, Milo, Fabrizio, Raparthy, Sharath Chandra, Gandhi, Kanishk, Abbasi, Baber, Phung, Duy, Iyer, Maia, Mahan, Dakota, Blagden, Chase, Gureja, Srishti, Hamdy, Mohammed, Li, Wen-Ding, Paolini, Giovanni, Ammanamanchi, Pawan Sasanka, Meyerson, Elliot
Synthetic data generation with Large Language Models is a promising paradigm for augmenting natural data over a nearly infinite range of tasks. Given this variety, direct comparisons among synthetic data generation algorithms are scarce, making it di
Externí odkaz:
http://arxiv.org/abs/2412.02980
Autor:
Joshi, Raviraj, Singla, Kanishk, Kamath, Anusha, Kalani, Raunak, Paul, Rakesh, Vaidya, Utkarsh, Chauhan, Sanjay Singh, Wartikar, Niranjan, Long, Eileen
Multilingual LLMs support a variety of languages; however, their performance is suboptimal for low-resource languages. In this work, we emphasize the importance of continued pre-training of multilingual LLMs and the use of translation-based synthetic
Externí odkaz:
http://arxiv.org/abs/2410.14815
Autor:
Gandhi, Kanishk, Lynch, Zoe, Fränken, Jan-Philipp, Patterson, Kayla, Wambu, Sharon, Gerstenberg, Tobias, Ong, Desmond C., Goodman, Noah D.
Understanding emotions is fundamental to human interaction and experience. Humans easily infer emotions from situations or facial expressions, situations from emotions, and do a variety of other affective cognition. How adept is modern AI at these in
Externí odkaz:
http://arxiv.org/abs/2409.11733
Autor:
He-Yueya, Joy, Ma, Wanjing Anya, Gandhi, Kanishk, Domingue, Benjamin W., Brunskill, Emma, Goodman, Noah D.
Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public policies. The obj
Externí odkaz:
http://arxiv.org/abs/2407.15645
Autor:
Nayak, Shravan, Jain, Kanishk, Awal, Rabiul, Reddy, Siva, van Steenkiste, Sjoerd, Hendricks, Lisa Anne, Stańczak, Karolina, Agrawal, Aishwarya
Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their performance has been typically assessed on general scene understandin
Externí odkaz:
http://arxiv.org/abs/2407.10920
Autor:
Horvitz, Zachary, Patel, Ajay, Singh, Kanishk, Callison-Burch, Chris, McKeown, Kathleen, Yu, Zhou
The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large langu
Externí odkaz:
http://arxiv.org/abs/2406.15586
Autor:
Fränken, Jan-Philipp, Zelikman, Eric, Rafailov, Rafael, Gandhi, Kanishk, Gerstenberg, Tobias, Goodman, Noah D.
When prompting a language model (LM), users often expect the model to adhere to a set of behavioral principles across diverse tasks, such as producing insightful content while avoiding harmful or biased language. Instilling such principles (i.e., a c
Externí odkaz:
http://arxiv.org/abs/2404.14313
Autor:
Fränken, Jan-Philipp, Gandhi, Kanishk, Qiu, Tori, Khawaja, Ayesha, Goodman, Noah D., Gerstenberg, Tobias
As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop systematic eval
Externí odkaz:
http://arxiv.org/abs/2404.10975
Autor:
Gandhi, Kanishk, Lee, Denise, Grand, Gabriel, Liu, Muxin, Cheng, Winson, Sharma, Archit, Goodman, Noah D.
Language models are rarely shown fruitful mistakes while training. They then struggle to look beyond the next token, suffering from a snowballing of errors and struggling to predict the consequence of their actions several steps ahead. In this paper,
Externí odkaz:
http://arxiv.org/abs/2404.03683
We propose an ensembling framework that uses diverse open-sourced Large Language Models (LLMs) to achieve high response quality while maintaining cost efficiency. We formulate a bi-objective optimization problem to represent the quality-cost tradeoff
Externí odkaz:
http://arxiv.org/abs/2312.16119