Zobrazeno 1 - 10
of 290
pro vyhledávání: '"Roy, Deb"'
While state-of-the-art Large Language Models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the quality of LLM
Externí odkaz:
http://arxiv.org/abs/2406.17737
Autor:
Kang, Wonjune, Roy, Deb
In this work, we introduce a framework for speech summarization that leverages the processing and reasoning capabilities of large language models (LLMs). We propose an end-to-end system that combines an instruction-tuned LLM with an audio encoder tha
Externí odkaz:
http://arxiv.org/abs/2406.05968
Autor:
Jiang, Hang, Zhang, Xiajie, Mahari, Robert, Kessler, Daniel, Ma, Eric, August, Tal, Li, Irene, Pentland, Alex 'Sandy', Kim, Yoon, Roy, Deb, Kabbara, Jad
Making legal knowledge accessible to non-experts is crucial for enhancing general legal literacy and encouraging civic participation in democracy. However, legal documents are often challenging to understand for people without legal backgrounds. In t
Externí odkaz:
http://arxiv.org/abs/2402.17019
Autor:
Fulay, Suyash, Roy, Deb
While political polarization has increased as measured through surveys, currently we lack comprehensive, longitudinal, and ecologically valid measurement of the polarization of online political speech that spans social media platforms. Using language
Externí odkaz:
http://arxiv.org/abs/2308.15556
Autor:
Brannon, William, Fulay, Suyash, Jiang, Hang, Kang, Wonjune, Roy, Brandon, Kabbara, Jad, Roy, Deb
We propose ConGraT(Contrastive Graph-Text pretraining), a general, self-supervised method for jointly learning separate representations of texts and nodes in a parent (or ``supervening'') graph, where each text is associated with one of the nodes. Da
Externí odkaz:
http://arxiv.org/abs/2305.14321
Despite the many use cases for large language models (LLMs) in creating personalized chatbots, there has been limited research on evaluating the extent to which the behaviors of personalized LLMs accurately and consistently reflect specific personali
Externí odkaz:
http://arxiv.org/abs/2305.02547
Autor:
Gillani, Nabeel, Beeferman, Doug, Overney, Cassandra, Vega-Pourheydarian, Christine, Roy, Deb
Educational data scientists often conduct research with the hopes of translating findings into lasting change through policy, civil society, or other channels. However, the bridge from research to practice can be fraught with sociopolitical frictions
Externí odkaz:
http://arxiv.org/abs/2304.08967
Identity spans multiple dimensions; however, the relative salience of a dimension of identity can vary markedly from person to person. Furthermore, there is often a difference between one's internal identity (how salient different aspects of one's id
Externí odkaz:
http://arxiv.org/abs/2304.07195
Public opinion reflects and shapes societal behavior, but the traditional survey-based tools to measure it are limited. We introduce a novel approach to probe media diet models -- language models adapted to online news, TV broadcast, or radio show co
Externí odkaz:
http://arxiv.org/abs/2303.16779
Autor:
Gillani, Nabeel, Beeferman, Doug, Vega-Pourheydarian, Christine, Overney, Cassandra, Van Hentenryck, Pascal, Roy, Deb
Most US school districts draw "attendance boundaries" to define catchment areas that assign students to schools near their homes, often recapitulating neighborhood demographic segregation in schools. Focusing on elementary schools, we ask: how much m
Externí odkaz:
http://arxiv.org/abs/2303.07603