3 citations · 4 across the 5 of their papers we have counts for
3 papers · 1 filter
ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering
Alexander Hoyle, Lorena Calvo-Bartolomé, Jordan Boyd-Graber +1
Topic model and document-clustering evaluations either use automated metrics that align poorly with human preferences or require expert labels that are intractable to scale. We des…
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Sander Schulhoff, Michael Ilie, Nishant Balepur +28
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these syst…
Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?
Sathvik Nair, Philip Resnik
An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words…