activity
20242026
collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Multimodal Conversation Structure Understanding

Kent K. Chang, Mackenzie Hanh Cramer, Anna Ho +3

While multimodal large language models (LLMs) excel at dialogue, whether they can adequately parse the structure of conversation -- conversational roles and threading -- remains un…

cs.CL2025

Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes

Li Lucy, Camilla Griffiths, Sarah Levine +3

Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrativ…

cs.CL2024

Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction

Kent K. Chang, Anna Ho, David Bamman

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the d…

cs.CL2024

On Classification with Large Language Models in Cultural Analytics

David Bamman, Kent K. Chang, Li Lucy +1

In this work, we survey the way in which classification is used as a sensemaking practice in cultural analytics, and assess where large language models can fit into this landscape.…

cs.CL2024

AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters

Li Lucy, Suchin Gururangan, Luca Soldaini +4

Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what data is retained or r…