Topic Segmentation Using Generative Language Models
Not on the map. Why?
Abstract (arXiv)
Topic segmentation using generative Large Language Models (LLMs) remains relatively unexplored. Previous methods use semantic similarity between sentences, but such models lack the long range dependencies and vast knowledge found in LLMs. In this work, we propose an overlapping and recursive prompting strategy using sentence enumeration. We also support the adoption of the boundary similarity evaluation metric. Results show that LLMs can be more effective segmenters than existing methods, but issues remain to be solved before they can be relied upon for topic segmentation.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 27 Dec 2025.
Builds on
10 of 20 references.
References · 10
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2018Text Segmentation as a Supervised Learning Taskcited by 76
- 2020Text Segmentation by Cross Segment Attentioncited by 54
- 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
- 2020Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentationcited by 41
- 2018Attention-based Neural Text Segmentationcited by 26
- 2021Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherencecited by 22
Built on by
Citing papers per year: 2026: 1.
1 paper.