Skip to main navigation Skip to search Skip to main content

D2CS - Documents Graph Clustering using LLM supervision

  • Yoel Ashkenazi
  • , Etzion Harari
  • , Regev Yehezkel Imra
  • , Dekel Cohen
  • , Naphtali Abudarham
  • , Yoram Louzoun
  • Bar-Ilan University
  • Rafael Advanced Defense Systems Ltd.
  • Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Knowledge discovery from large-scale, heterogeneous textual corpora presents a significant challenge. Document clustering offers a practical solution by organizing unstructured texts into coherent groups based on content and thematic similarity. However, clustering does not inherently ensure thematic consistency. Here, we propose a novel framework that constructs a similarity graph over document embeddings and applies iterative graph-based clustering algorithms to partition the corpus into initial clusters. To overcome the limitations of conventional methods in producing semantically consistent clusters, we incorporate iterative feedback from a large language model (LLM) to guide the refinement process. The LLM is used to assess cluster quality and adjust edge weights within the graph, promoting better intra-cluster cohesion and inter-cluster separation. The LLM guidance is based on a set of success Rate metrics that we developed to measure the semantic coherence of clusters. Experimental results on multiple benchmark datasets demonstrate that the iterative process and additional user-supplied a priori edges improve the summaries’ consistency and fluency, highlighting the importance of known connections among the documents. The removal of very rare or very frequent sentences has a mixed effect on the quality scores. Our full code is available here: https://github.com/D2CS-sub/D2CS.

Original languageEnglish
Title of host publicationEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
EditorsChristos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
PublisherAssociation for Computational Linguistics (ACL)
Pages23606-23623
Number of pages18
ISBN (Electronic)9798891763357
DOIs
StatePublished - 2025
Event30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Suzhou, China
Duration: 4 Nov 2025 → 9 Nov 2025

Publication series

NameEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025

Conference

Conference30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Country/TerritoryChina
CitySuzhou
Period4/11/25 → 9/11/25

Bibliographical note

Publisher Copyright:
© 2025 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'D2CS - Documents Graph Clustering using LLM supervision'. Together they form a unique fingerprint.

Cite this