Zobrazeno 1 - 10
of 163
pro vyhledávání: '"RESNIK, PHILIP"'
Autor:
Resnik, Philip
This paper's primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models. We do this by seeking to convince the reader that harmful biases are an inevitable consequence aris
Externí odkaz:
http://arxiv.org/abs/2406.13138
Autor:
Premananth, Gowtham, Siriwardena, Yashish M., Resnik, Philip, Bansal, Sonia, Kelly, Deanna L., Espy-Wilson, Carol
This paper presents a novel multimodal framework to distinguish between different symptom classes of subjects in the schizophrenia spectrum and healthy controls using audio, video, and text modalities. We implemented Convolution Neural Network and Lo
Externí odkaz:
http://arxiv.org/abs/2406.09706
Autor:
Schulhoff, Sander, Ilie, Michael, Balepur, Nishant, Kahadze, Konstantine, Liu, Amanda, Si, Chenglei, Li, Yinheng, Gupta, Aayush, Han, HyoJung, Schulhoff, Sevien, Dulepet, Pranav Sandeep, Vidyadhara, Saurav, Ki, Dayeon, Agrawal, Sweta, Pham, Chau, Kroiz, Gerson, Li, Feileen, Tao, Hudson, Srivastava, Ashay, Da Costa, Hevander, Gupta, Saloni, Rogers, Megan L., Goncearenco, Inna, Sarli, Giuseppe, Galynker, Igor, Peskoff, Denis, Carpuat, Marine, White, Jules, Anadkat, Shyamal, Hoyle, Alexander, Resnik, Philip
Generative Artificial Intelligence (GenAI) systems are being increasingly deployed across all parts of industry and research settings. Developers and end users interact with these systems through the use of prompting or prompt engineering. While prom
Externí odkaz:
http://arxiv.org/abs/2406.06608
Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users minimal contro
Externí odkaz:
http://arxiv.org/abs/2311.01449
Autor:
Nair, Sathvik, Resnik, Philip
An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by comparing
Externí odkaz:
http://arxiv.org/abs/2310.17774
This study focuses on how different modalities of human communication can be used to distinguish between healthy controls and subjects with schizophrenia who exhibit strong positive symptoms. We developed a multi-modal schizophrenia classification sy
Externí odkaz:
http://arxiv.org/abs/2309.15136
Most prior and current research examining misinformation spread on social media focuses on reports published by 'fake' news sources. These approaches fail to capture another potential form of misinformation with a much larger audience: factual news f
Externí odkaz:
http://arxiv.org/abs/2308.06459
When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a
Externí odkaz:
http://arxiv.org/abs/2305.14583
Stressors are related to depression, but this relationship is complex. We investigate the relationship between open-ended text responses about stressors and depressive symptoms across gender and racial/ethnic groups. First, we use topic models and ot
Externí odkaz:
http://arxiv.org/abs/2211.07932
Recently, the relationship between automated and human evaluation of topic models has been called into question. Method developers have staked the efficacy of new topic model variants on automated measures, and their failure to approximate human pref
Externí odkaz:
http://arxiv.org/abs/2210.16162