Controllable Clustering with LLM-driven Embeddings

Given the inherent subjectivity of similarity in text, fully unsupervised text clustering is unlikely to produce groupings that are relevant across a variety of use cases. Traditional techniques to guide clustering rely on costly, time-consuming human feedback and/or pre-existing labels. Leveraging recent advancements in LLMs and decoder-only embedding models, this project presents techniques to effectively control text embeddings with minimal human input: instruction prefixing and LLM preprocessing. We evaluate clustering performance for datasets with multiple independent ground-truth labels, or perspectives, and find that these techniques can be used to improve clustering for one perspective or use case, at the cost of a tradeoff in performance for another use case.

[Paper]: Pang-Naylor, K., Manivasagan, S., Zhong, A., Garg, M., Mondello, N., Buckner, B., Chang, J., Mahajan, K., Hashemi, M., & Casati, F. (2025). Controllable clustering with LLM-driven embeddings. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track (pp. 686–702). Association for Computational Linguistics.