Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Swayamdipta, Swabha"'
Subjective tasks in NLP have been mostly relegated to objective standards, where the gold label is decided by taking the majority vote. This obfuscates annotator disagreement and the inherent uncertainty of the label. We argue that subjectivity shoul
Externí odkaz:
http://arxiv.org/abs/2408.14141
Autor:
Gulati, Aryan, Dong, Xingjian, Hurtado, Carlos, Shekkizhar, Sarath, Swayamdipta, Swabha, Ortega, Antonio
As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data
Externí odkaz:
http://arxiv.org/abs/2407.13141
Human evaluation of generated language through pairwise preference judgments is pervasive. However, under common scenarios, such as when generations from a model pair are very similar, or when stochastic decoding results in large variations in genera
Externí odkaz:
http://arxiv.org/abs/2407.01878
Autor:
Ranjit, Jaspreet, Joshi, Brihi, Dorn, Rebecca, Petry, Laura, Koumoundouros, Olga, Bottarini, Jayne, Liu, Peichen, Rice, Eric, Swayamdipta, Swabha
Warning: Contents of this paper may be upsetting. Public attitudes towards key societal issues, expressed on online media, are of immense value in policy and reform efforts, yet challenging to understand at scale. We study one such social issue: home
Externí odkaz:
http://arxiv.org/abs/2406.14883
Autor:
Cui, Xinyue, Swayamdipta, Swabha
Despite the remarkable generative capabilities of language models in producing naturalistic language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate the task of
Externí odkaz:
http://arxiv.org/abs/2406.04834
The commercialization of large language models (LLMs) has led to the common practice of high-level API-only access to proprietary models. In this work, we show that even with a conservative assumption about the model architecture, it is possible to l
Externí odkaz:
http://arxiv.org/abs/2403.09539
Despite great advances in program synthesis techniques, they remain algorithmic black boxes. Although they guarantee that when synthesis is successful, the implementation satisfies the specification, they provide no additional information regarding h
Externí odkaz:
http://arxiv.org/abs/2403.03429
Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation for the effectiveness of the truncation sampling by proving that truncat
Externí odkaz:
http://arxiv.org/abs/2310.01693
Autor:
Nam, Yoonsoo, Lehavi, Adam, Yang, Daniel, Bose, Digbalay, Swayamdipta, Swabha, Narayanan, Shrikanth
Video summarization remains a huge challenge in computer vision due to the size of the input videos to be summarized. We propose an efficient, language-only video summarizer that achieves competitive accuracy with high data efficiency. Using only tex
Externí odkaz:
http://arxiv.org/abs/2309.09405
Autor:
Zhou, Xuhui, Zhu, Hao, Yerukola, Akhila, Davidson, Thomas, Hwang, Jena D., Swayamdipta, Swabha, Sap, Maarten
Warning: This paper contains content that may be offensive or upsetting. Understanding the harms and offensiveness of statements requires reasoning about the social and situational context in which statements are made. For example, the utterance "you
Externí odkaz:
http://arxiv.org/abs/2306.01985