← Search

Lorena Calvo-Bartolomé

2 accepted papers

2025

Large Language Models Struggle to Describe the Haystack without Human Help: A Social Science-Inspired Evaluation of Topic Models

ACL 2025long

A common use of NLP is to facilitate the understanding of large document collections, with models based on Large Language Models (LLMs) replacing probabilistic topic models. Yet the effectiveness of LLM-based approaches in real-world applications remains under explored. This study measures the knowl…

2025

ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering

ACL 2025long

Topic models and document-clustering evaluations either use automated metrics that align poorly with human preferences, or require expert labels that are intractable to scale. We design a scalable human evaluation protocol and a corresponding automated approximation that reflect practitioners’ real-…