Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Chakrabarty, Tuhin"'
LLM-based applications are helping people write, and LLM-generated text is making its way into social media, journalism, and our classrooms. However, the differences between LLM-generated and human-written text remain unclear. To explore this, we hir
Externí odkaz:
http://arxiv.org/abs/2409.14509
Autor:
Samadarshi, Prisha, Mustafa, Mariam, Kulkarni, Anushka, Rothkopf, Raven, Chakrabarty, Tuhin, Muresan, Smaranda
The New York Times Connections game has emerged as a popular and challenging pursuit for word puzzle enthusiasts. We collect 438 Connections games to evaluate the performance of state-of-the-art large language models (LLMs) against expert and novice
Externí odkaz:
http://arxiv.org/abs/2406.11012
Autor:
Chakrabarty, Tuhin
Large language models (LLMs) constitute a paradigm shift in Natural Language Processing and Artificial Intelligence. In this thesis, I explore the integration of creative capabilities into artificial intelligence systems to enhance their interaction
Large Vision-Language Models (VLMs) have demonstrated strong capabilities in tasks requiring a fine-grained understanding of literal meaning in images and text, such as visual question-answering or visual entailment. However, there has been little ex
Externí odkaz:
http://arxiv.org/abs/2405.01474
Autor:
Yang, Chenghao, Chakrabarty, Tuhin, Hochstatter, Karli R, Slavin, Melissa N, El-Bassel, Nabila, Muresan, Smaranda
In the last decade, the United States has lost more than 500,000 people from an overdose involving prescription and illicit opioids making it a national public health emergency (USDHHS, 2017). Medical practitioners require robust and timely tools tha
Externí odkaz:
http://arxiv.org/abs/2311.09066
Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of instructions) 2) grou
Externí odkaz:
http://arxiv.org/abs/2310.19145
Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the creativity of a piece of writing is challenging. Inspired by the Torrance Test of Creative
Externí odkaz:
http://arxiv.org/abs/2309.14556
The development of large language models (LLMs) capable of following instructions and engaging in conversational interactions sparked increased interest in their utilization across various support tools. We investigate the utility of modern LLMs in a
Externí odkaz:
http://arxiv.org/abs/2309.12570
Autor:
Chakrabarty, Tuhin, Saakyan, Arkadiy, Winn, Olivia, Panagopoulou, Artemis, Yang, Yue, Apidianaki, Marianna, Muresan, Smaranda
Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a new task
Externí odkaz:
http://arxiv.org/abs/2305.14724
Publikováno v:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8172 - 8187
Fallacies are used as seemingly valid arguments to support a position and persuade the audience about its validity. Recognizing fallacies is an intrinsically difficult task both for humans and machines. Moreover, a big challenge for computational mod
Externí odkaz:
http://arxiv.org/abs/2301.09992