Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Rogers, Timothy T"'
Autor:
Chuang, Yun-Shiuan, Nirunwiroj, Krirk, Studdiford, Zach, Goyal, Agam, Frigo, Vincent V., Yang, Sijia, Shah, Dhavan, Hu, Junjie, Rogers, Timothy T.
Publikováno v:
Findings of the Association for Computational Linguistics (ACL): EMNLP 2024
Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study assessed whether LLM alignment wi
Externí odkaz:
http://arxiv.org/abs/2406.17232
Concepts, both abstract and concrete, elicit a distribution of association strengths across perceptual color space, which influence aspects of visual cognition ranging from object recognition to interpretation of information visualizations. While pri
Externí odkaz:
http://arxiv.org/abs/2406.17781
Our interaction with others largely hinges on how we semantically organize the social world. The organization of such conceptual information is not static -- as we age, our experiences and ever-changing anatomy alter how we represent and arrange sema
Externí odkaz:
http://arxiv.org/abs/2404.15151
Whereas cognitive models of learning often assume direct experience with both the features of an event and with a true label or outcome, much of everyday learning arises from hearing the opinions of others, without direct access to either the experie
Externí odkaz:
http://arxiv.org/abs/2402.13927
Autor:
Chuang, Yun-Shiuan, Suresh, Siddharth, Harlalka, Nikunj, Goyal, Agam, Hawkins, Robert, Yang, Sijia, Shah, Dhavan, Hu, Junjie, Rogers, Timothy T.
Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language Models (LLMs)
Externí odkaz:
http://arxiv.org/abs/2311.09665
Autor:
Chuang, Yun-Shiuan, Wu, Yi, Gupta, Dhruv, Uppaal, Rheeya, Kumar, Ananya, Sun, Luhang, Sreedhar, Makesh Narsimhan, Yang, Sijia, Rogers, Timothy T., Hu, Junjie
Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection. This study benchmarks the effectiveness of evolving domain
Externí odkaz:
http://arxiv.org/abs/2311.09661
Autor:
Chuang, Yun-Shiuan, Goyal, Agam, Harlalka, Nikunj, Suresh, Siddharth, Hawkins, Robert, Yang, Sijia, Shah, Dhavan, Hu, Junjie, Rogers, Timothy T.
Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-s
Externí odkaz:
http://arxiv.org/abs/2311.09618
Autor:
Vartanian, Ara, Sun, Xiaoxi, Chuang, Yun-Shiuan, Suresh, Siddharth, Zhu, Xiaojin, Rogers, Timothy T.
This paper considers how interactions with AI algorithms can boost human creative thought. We employ a psychological task that demonstrates limits on human creativity, namely semantic feature generation: given a concept name, respondents must list as
Externí odkaz:
http://arxiv.org/abs/2311.10127
Autor:
Chuang, Yun-Shiuan, Rogers, Timothy T.
Understanding how an individual changes its attitude, belief, and opinion due to other people's social influences is vital because of its wide implications. A core methodology that is used to study the change of attitude under social influences is ag
Externí odkaz:
http://arxiv.org/abs/2306.03446
This study evaluates the potential of a large language model for aiding in generation of semantic feature norms - a critical tool for evaluating conceptual structure in cognitive science. Building from an existing human-generated dataset, we show tha
Externí odkaz:
http://arxiv.org/abs/2304.05591