Confabulation: The surprising value of large language model hallucinations

P Sui, E Duede, S Wu, RJ So - arxiv preprint arxiv:2406.04175, 2024 - arxiv.org
This paper presents a systematic defense of large language model (LLM) hallucinations
or'confabulations' as a potential resource instead of a categorically negative pitfall. The …

Identifying narrative content in podcast transcripts

Y Abdessamed, S Rezapour… - Proceedings of the 18th …, 2024 - aclanthology.org
As one of the oldest forms of human communication, narratives appear across a variety of
genres and media. Computational methods have been applied to study narrativity in novels …

Fora: A corpus and framework for the study of facilitated dialogue

H Schroeder, D Roy, J Kabbara - … of the 62nd Annual Meeting of …, 2024 - aclanthology.org
Facilitated dialogue is increasingly popular as a method of civic engagement and as a
method for gathering social insight, but resources for its study are scant. We present Fora, a …

Rhetoric of/with AI: An Introduction

ZP Majdik, SS Graham - Rhetoric Society Quarterly, 2024 - Taylor & Francis
Damien Pfister and S. Scott Graham, likewise, draw significantly on research in critical
algorithm studies to make their arguments about Google Glass and Health AI, respectively …

Natural Language Generation from Visual Sequences: Challenges and Future Directions

AK Surikuchi, R Fernández, S Pezzelle - arxiv preprint arxiv:2502.13034, 2025 - arxiv.org
The ability to use natural language to talk about visual content is at the core of human
intelligence and a crucial feature of any artificial intelligence system. Various studies have …

Large Scale Narrative Messaging around Climate Change: A Cross-Cultural Comparison

H Zhou, D Hobson, D Ruths, A Piper - Proceedings of the 1st …, 2024 - aclanthology.org
In this study, we explore the use of Large Language Models (LLMs) such as GPT-4 to extract
and analyze the latent narrative messaging in climate change-related news articles from …