collaborators
Showing cs.CLShow all

27 papers · 1 filter

cs.CL2026

Diffusion Language Models Are Natively Length-Aware

Vittorio Rossi, Giacomo Cirò, Davide Beltrame +3

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fi…

cs.CL2026

Do Large Language Models Adapt to Language Variation across Socioeconomic Status?

Elisa Bassignana, Mike Zhang, Dirk Hovy +1

Humans adjust their linguistic style to the audience they are addressing. However, the extent to which LLMs adapt to different social contexts is largely unknown. As these models i…

cs.CL2026

PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors

Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva +4

Recent advances in large language models (LLMs) demonstrate their potential as educational tutors. However, different tutoring strategies benefit different student personalities, a…

cs.CL2026

Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?

Jingwei Ni, Yu Fan, Vilém Zouhar +6

Variation in human annotation (i.e., disagreements) is common in NLP, often reflecting important information like task subjectivity and sample ambiguity. Modeling this variation is…

cs.CL2025

Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings

Cesar Gonzalez-Gutierrez, Dirk Hovy

Prompting is a common approach for leveraging LMs in zero-shot settings. However, the underlying mechanisms that enable LMs to perform diverse tasks without task-specific supervisi…

cs.CL2025

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation

Joachim Baumann, Paul Röttger, Aleksandra Urman +4

Large language models are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outp…