@article{pal-etal-2026-disentangling,
    title = "Disentangling Approaches to Conversation Disentanglement: Fine-Tune or Learn from Scratch?",
    author = "Pal, Debaditya  and
      Leuski, Anton  and
      Artstein, Ron  and
      Traum, David  and
      Georgila, Kallirroi",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.229/",
    pages = "2927--2941",
    abstract = "Conversation disentanglement is the process of segmenting a stream of messages or utterances into separate conversations or ``threads'' that can be more easily understood and processed. We compare the performance of GPT-4o and GPT-4o Mini with deep learning models built from scratch for this task. We show that, using the same amount of training data, out-of-the-box GPT-4o performs poorly, and fine-tuning GPT-4o Mini results in performance comparable to learning small-size models from scratch (based on standard hand-crafted features for this task), with performance reaching 74.4{\%} F1-score for prediction of links between messages and 45.3{\%} F1-score for prediction of perfectly matching conversations. However, the fine-tuned GPT-4o Mini model underperforms when compared to models that utilize complex structural information. We also provide a new method for detailed analysis of the successes and failures of our models, and a new visualization method."
}