Richard So

2 accepted papers

2024

Confabulation: The Surprising Value of Large Language Model Hallucinations

Peiqi Sui, Eamon Duede, Sophie Wu, Richard So

ACL 2024long

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 standard view is that confabulations are inherently problematic and AI research should eliminate this flaw. In this paper…

Cited by 22 Source ↗PDF ↗Scholar ↗

2020

Transfer Learning from Youtube Soundtracks to Tag Arctic Ecoacoustic Recordings

Enis Berk Çoban, Dara Pir, Richard So, Michael I. Mandel

ICASSP 2020accepted

Sound provides a valuable tool for long-term monitoring of sensitive animal habitats at a spatial scale larger than camera traps or field observations, while also providing more details than satellite imagery. Currently, the ability to collect such recordings outstrips the ability to analyze them ma…

Cited by 0 Source ↗Scholar ↗