Zobrazeno 1 - 10
of 896
pro vyhledávání: '"Vashistha P"'
This paper examines how large language models (LLMs) can help people write constructive comments in online debates on divisive social issues and whether the notions of constructiveness vary across cultures. Through controlled experiments with 600 par
Externí odkaz:
http://arxiv.org/abs/2411.03295
Autor:
Hamna, Sudharsan, Deepthi, Seth, Agrima, Budhiraja, Ritvik, Khullar, Deepika, Jain, Vyshak, Bali, Kalika, Vashistha, Aditya, Segal, Sameer
Large Language Models (LLMs) and Text-To-Image (T2I) models have demonstrated the ability to generate compelling text and visual stories. However, their outputs are predominantly aligned with the sensibilities of the Global North, often resulting in
Externí odkaz:
http://arxiv.org/abs/2410.19419
Autor:
Vashistha, Shikhar, Kumar, Neetesh
Traditional graph neural networks (GNNs) lack scalability and lose individual node characteristics due to over-smoothing, especially in the case of deeper networks. This results in sub-optimal feature representation, affecting the model's performance
Externí odkaz:
http://arxiv.org/abs/2410.15849
People with disabilities (PwD) regularly encounter ableist hate and microaggressions online. While online platforms use machine learning models to moderate online harm, there is little research investigating how these models interact with ableism. In
Externí odkaz:
http://arxiv.org/abs/2410.03448
Autor:
Hao, Yuexing, Holmes, Jason, Waddle, Mark, Yu, Nathan, Vickers, Kirstin, Preston, Heather, Margolin, Drew, Löckenhoff, Corinna E., Vashistha, Aditya, Ghassemi, Marzyeh, Kalantari, Saleh, Liu, Wei
Cancer patients often struggle to transition swiftly to treatment due to limited institutional resources, lack of sophisticated professional guidance, and low health literacy. The emergence of Large Language Models (LLMs) offers new opportunities for
Externí odkaz:
http://arxiv.org/abs/2409.19100
Large language models (LLMs) are being increasingly integrated into everyday products and services, such as coding tools and writing assistants. As these embedded AI applications are deployed globally, there is a growing concern that the AI models un
Externí odkaz:
http://arxiv.org/abs/2409.11360
Autor:
Ramjee, Pragnya, Chhokar, Mehak, Sachdeva, Bhuvan, Meena, Mahendra, Abdullah, Hamid, Vashistha, Aditya, Nagar, Ruchit, Jain, Mohit
Community health workers (CHWs) provide last-mile healthcare services but face challenges due to limited medical knowledge and training. This paper describes the design, deployment, and evaluation of ASHABot, an LLM-powered, experts-in-the-loop, What
Externí odkaz:
http://arxiv.org/abs/2409.10913
Many social and environmental phenomena are associated with macroscopic changes in the built environment, captured by satellite imagery on a global scale and with daily temporal resolution. While widely used for prediction, these images and especiall
Externí odkaz:
http://arxiv.org/abs/2407.11674
This research studies the nature and spread of WhatsApp content among everyday users in a rural Indian village. Leveraging a dataset of hundreds of private WhatsApp groups collected with consent from participants, our study uncovers the kinds of What
Externí odkaz:
http://arxiv.org/abs/2407.08172
WhatsApp groups have become a hotbed for the propagation of harmful content including misinformation, hate speech, polarizing content, and rumors, especially in Global South countries. Given the platform's end-to-end encryption, moderation responsibi
Externí odkaz:
http://arxiv.org/abs/2405.20254