Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Rao, Delip"'
Retractions play a vital role in maintaining scientific integrity, yet systematic studies of retractions in computer science and other STEM fields remain scarce. We present WithdrarXiv, the first large-scale dataset of withdrawn papers from arXiv, co
Externí odkaz:
http://arxiv.org/abs/2412.03775
Style representation learning builds content-independent representations of author style in text. Stylometry, the analysis of style in text, is often performed by expert forensic linguists and no large dataset of stylometric annotations exists for tr
Externí odkaz:
http://arxiv.org/abs/2305.12696
Autor:
Lyu, Qing, Havaldar, Shreya, Stein, Adam, Zhang, Li, Rao, Delip, Wong, Eric, Apidianaki, Marianna, Callison-Burch, Chris
While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Fait
Externí odkaz:
http://arxiv.org/abs/2301.13379
Autor:
McMahan, Brian, Rao, Delip
We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations from an un
Externí odkaz:
http://arxiv.org/abs/1710.08377
Publikováno v:
Multi-source, Multilingual Information Extraction & Summarization; 2013, p93-115, 23p
Publikováno v:
Proceedings of the 2nd International Workshop: Search & Mining User-generated Contents; 10/30/2010, p37-44, 8p
Publikováno v:
PRICAI 2006: Trends in Artificial Intelligence; 2006, p474-483, 10p