Pith. sign in

REVIEW 8 cited by

Text Clustering with Large Language Model Embeddings

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.15112 v5 pith:UCPZFAEG submitted 2024-03-22 cs.CL cs.AIcs.LG

Alina Petukhova , João P. Matos-Carvalho , Nuno Fachada This is my paper · ORCID
classification cs.CLcs.AIcs.LG
keywords clusteringtextembeddingsmodellanguagellmsresultstextual
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the selection of textual embeddings and clustering algorithms. This study argues that recent advancements in large language models (LLMs) have the potential to enhance this task. The research investigates how different textual embeddings, particularly those utilised in LLMs, and various clustering algorithms influence the clustering of text datasets. A series of experiments were conducted to evaluate the impact of embeddings on clustering results, the role of dimensionality reduction through summarisation, and the adjustment of model size. The findings indicate that LLM embeddings are superior at capturing subtleties in structured language. OpenAI's GPT-3.5 Turbo model yields better results in three out of five clustering metrics across most tested datasets. Most LLM embeddings show improvements in cluster purity and provide a more informative silhouette score, reflecting a refined structural understanding of text data compared to traditional methods. Among the more lightweight models, BERT demonstrates leading performance. Additionally, it was observed that increasing model dimensionality and employing summarisation techniques do not consistently enhance clustering efficiency, suggesting that these strategies require careful consideration for practical application. These results highlight a complex balance between the need for refined text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by integrating embeddings from LLMs, offering improved methodologies and suggesting new avenues for future research in various types of textual analysis.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review

    cs.HC 2025-01 conditional novelty 7.0 of 10

    A systematic review of 153 CHI papers shows LLMs are used across ten domains, mostly as system engines and in empirical or artifact contributions, with widespread validity and reproducibility concerns.

  2. Cequel: Cost-Effective Querying of Large Language Models for Text Clustering

    cs.CL 2025-04 conditional novelty 6.0 of 10

    Cequel reduces the LLM query cost of text clustering by selecting a few informative text pairs or triples, turning LLM answers into must-link and cannot-link constraints, and clustering with a PMI-weighted constrained...

  3. A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering

    cs.IR 2025-06 conditional novelty 5.0 of 10

    LLM embeddings clustered with HDBSCAN group 6,390 NIH common data elements into 118 semantic clusters, and a random forest on the same embeddings reaches 90.46% accuracy on cluster labels.

  4. BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment

    cs.CL 2024-11 conditional novelty 5.0 of 10

    BPO balances knowledge breadth and depth in preference data by compressing prompts and dynamically augmenting the number of response pairs per prompt using gradient-based clustering, achieving stronger alignment with ...

  5. AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research

    cs.AI 2025-05 conditional novelty 4.0 of 10

    The paper defines a five-level AI4SoS automation hierarchy and demonstrates a preliminary LLM multi-agent society that partially reproduces known correlations between team diversity and citation impact.

  6. A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A review that organizes LLM uncertainty quantification into token-level, self-verbalized, semantic-similarity, and mechanistic interpretability categories.

  7. Advanced Topic Modeling Techniques for Categorizing Software Vulnerabilities

    cs.CR 2026-07 reject novelty 2.5 of 10

    Existing embedding-based topic models produce interpretable clusters on Cisco vulnerability Threat text, but without quantitative coherence scores, baselines, or downstream prioritization metrics.

  8. LLMs are Also Effective Embedding Models: An In-depth Overview

    cs.CL 2024-12 conditional novelty 2.0 of 10

    A structured survey of using decoder-only LLMs as text embedding models, covering prompting, fine-tuning, data construction, benchmarks, and open problems.

Pith tools