Ranked Multi-Label-Augmented Topic Modeling for Legislative Content Profiling
Source abstract
Abstract
Navigating extensive legislative corpora is often impeded by the linguistic complexity inherent in legal texts. To address this, we present a novel topic representation learning method designed to facilitate the systematic exploration of legislative content. We demonstrate the efficacy of this approach by applying it to the vast corpus of Italian legislation comprising about 74 k laws with more than 300 k articles. While current topic models group documents by latent semantic similarity, they often lack the granularity required for precise navigation. Our approach augments these representations by integrating our topic modeling framework with multi-label profiles. We enrich the representation of individual laws by extracting and ranking the top 10 keywords based on their relevance to the enclosing topic, subsequently aggregating these rankings to construct a comprehensive, alternative description of the broader legal themes. By bridging latent semantic clusters with explicit, LLM-generated labels, this method yields a highly interpretable representation of the corpus, significantly enhancing the profiling and navigability of complex legislative content. We improve over our baseline representation in 74.67% of cases, showing potential for re-use in highly specialized text corpora.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Artificial Intelligence in Law · Topic Modeling · Computational and Text Analysis Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milan, Italy
Funding
TEThYS
References (52)
Show source-provided references
1. Exploring the use of LLMs in the Italian legal domain: A survey on recent applications10.1016/j.clsr.2025.106164 ↗
2. Palmirani, M., and Vitali, F. (2011). Akoma-Ntoso for legal documents. Legislative XML for the Semantic Web: Principles, Models, Standards for Document Management, Springer.10.1007/978-94-007-1887-6_6 ↗
3. Colombo, A. (2024, January 21–25). Leveraging knowledge graphs and LLMs to support and monitor legislative systems. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, Boise, ID, USA.10.1145/3627673.3680268 ↗
4. Colombo, A., Cambria, F., and Invernici, F. (2025, January 25). Legislative knowledge management with property graphs. Proceedings of the Workshops of the EDBT/ICDT 2025 Joint Conference Co-Located with the EDBT/ICDT 2025 Joint Conference, Barcelona, Spain.
5. Topic modeling algorithms and applications: A survey10.1016/j.is.2022.102131 ↗
6. Neural topic modeling reveals German television’s climate change coverage10.1038/s43247-025-02402-1 ↗
7. Growing polarization around climate change on social media10.1038/s41558-022-01527-x ↗
8. Capturing research literature attitude towards sustainable development goals: An LLM-based topic modeling approach10.1186/s40537-025-01189-4 ↗
9. Obadimu, A., Mead, E., and Agarwal, N. (2019, January 24–28). Identifying latent toxic features on YouTube using non-negative matrix factorization. Proceedings of the Ninth International Conference on Social Media Technologies, Communication, and Informatics, Valencia, Spain.
10. Latent dirichlet allocation
11. Sia, S., Dalmia, A., and Mielke, S.J. (2020, January 16–20). Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.135 ↗
12. Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv.
13. Bernasconi, A., Invernici, F., and Ceri, S. (2024, January 3–7). TETYS: Towards the Next-Generation Open-Source Web Topic Explorer. Proceedings of the CEUR PROCEEDINGS, CEUR-WS, Limassol, Cyprus.
14. Exploring the evolution of research topics during the COVID-19 pandemic10.1016/j.eswa.2024.124028 ↗
15. Exploring the political agenda of the european parliament using a dynamic topic modeling approach10.1017/pan.2016.7 ↗
16. Observing political and societal changes in Finnish parliamentary speech data, 1980–2010, with topic modelling10.1080/02606755.2023.2213550 ↗
17. Herget, K., Yeung, J.E., Rufrano, M., and Alegre, T. (2026, March 27). Exploring Semantic-Thematic Fields and Lexical Patterns in Parliamentary Debates—Topic Modeling Across Comparable Corpora. Available online: https://gredos.usal.es/handle/10366/164227.10.14201/0AQ0373559569 ↗
18. O’Neill, J., Robin, C., O’Brien, L., and Buitelaar, P. (2017, January 16). An analysis of topic modelling for legislative texts. Proceedings of the CEUR Workshop Proceedings, London, UK.
19. Vīksna, R., Kirikova, M., and Kiopa, D. (2020, January 9). Exploring the use of topic analysis in latvian legal documents. Proceedings of the First International Workshop “CAiSE for Legal Documents” (COUrT 2020) Co-Located with the 32nd International Conference on Advanced Information Systems Engineering (CAiSE 2020), Grenoble, France.
20. Silveira, R., Fernandes, C.G.G., Monteiro Neto, J.A., Furtado, J.J.V.P., and Pimentel Filho, J.E. (2021, January 25). Topic Modelling of Legal Documents via LEGAL-BERT. Proceedings of the First International Workshop RELATED—Relations in the Legal Domain Co-Located with the 18th International Conference on Artificial Intelligence and Law (ICAIL), São Paulo, Brazil.
21. Aguiar, A., Silveira, R., Furtado, V., Pinheiro, V., and Neto, J.A.M. (2022). Using topic modeling in classification of Brazilian lawsuits. Proceedings of the International Conference on Computational Processing of the Portuguese Language, Springer.10.1007/978-3-030-98305-5_22 ↗
22. Didwania, K., Toshniwal, D., and Agarwal, A. (2024, January 15–19). Unveiling Themes in Judicial Proceedings: A Cross-Country Study Using Topic Modeling on Legal Documents from India and the UK. Proceedings of the Joint Ontology Workshops (JOWO) Co-Located with the 14th International Conference on Formal Ontology in Information Systems (FOIS), Enschede, The Netherlands.
23. Bridging spherical mixture distributions and word semantic knowledge for Neural Topic Modeling10.1016/j.eswa.2024.124850 ↗
24. NMTF-LTM: Towards an Alignment of Semantics for Lifelong Topic Modeling10.1109/TKDE.2023.3267496 ↗
25. Topic Modeling on Document Networks With Dirichlet Optimal Transport Barycenter10.1109/TKDE.2023.3303465 ↗
26. Graph Contrastive Topic Model10.1016/j.eswa.2024.124631 ↗
27. Mu, Y., Dong, C., Bontcheva, K., and Song, X. (2024). Large language models offer an alternative to the traditional approach of topic modelling. arXiv.10.63317/2x489fw7wi5m ↗
28. Pham, C.M., Hoyle, A., Sun, S., Resnik, P., and Iyyer, M. (2024, January 16–21). TopicGPT: A Prompt-based Topic Modeling Framework. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Mexico City, Mexico.10.18653/v1/2024.naacl-long.164 ↗
29. Xu, W., Hu, W., Wu, F., and Sengamedu, S. (2023, January 6–10). DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.10.18653/v1/2023.findings-emnlp.606 ↗
30. An LLM-assisted ETL pipeline to build a high-quality knowledge graph of the Italian legislation10.1016/j.ipm.2025.104082 ↗
31. Large language models for efficient topic modeling10.1007/s00521-025-11593-9 ↗
32. Truica, C.O., Radulescu, F., and Boicea, A. (2016, January 24–27). Comparing different term weighting schemas for topic modeling. Proceedings of the 2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), Timisoara, Romania.10.1109/SYNASC.2016.055 ↗
33. Wang, H., Prakash, N., Hoang, N.K., Hee, M.S., Naseem, U., and Lee, R.K.W. (2023, January 15–18). Prompting large language models for topic modeling. Proceedings of the 2023 IEEE International Conference on Big Data (BigData), Sorrento, Italy.10.1109/BigData59044.2023.10386113 ↗
34. Exploring coherent topics by topic modeling with term weighting10.1016/j.ipm.2018.05.009 ↗
35. Topic modeling in embedding spaces10.1162/tacl_a_00325 ↗
36. Invernici, F., Bernasconi, A., Curati, F., Jakimov, J., and Samavi, A. (2025, January 25–28). TETYS: Configurable Topic Modeling Exploration for Big Corpora of Text Documents. Proceedings of the 28th International Conference on Extending Database Technology (EDBT), Barcelona, Spain.
37. Honnibal, M., Montani, I., Van Landeghem, S., and Boyd, A. (2026, March 18). spaCy: Industrial-Strength Natural Language Processing in Python. Available online: https://spacy.io/.
38. Reimers, N., and Gurevych, I. (2020, January 16–20). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.365 ↗
39. Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., and Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv.
40. (2026, March 18). MTEB Leaderboard. Available online: https://huggingface.co/spaces/mteb/leaderboard.
41. McInnes, L., Healy, J., and Melville, J. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv.10.21105/joss.00861 ↗
42. hdbscan: Hierarchical density based clustering10.21105/joss.00205 ↗
43. Moulavi, D., Jaskowiak, P.A., Campello, R.J., Zimek, A., and Sander, J. (2014, January 24–26). Density-Based Clustering Validation. Proceedings of the 2014 SIAM International Conference on Data Mining, Philadelphia, PA, USA.10.1137/1.9781611973440.96 ↗
44. Terragni, S., Fersini, E., Galuzzi, B.G., Tropeano, P., and Candelieri, A. (2021, January 19–23). OCTIS: Comparing and Optimizing Topic models is Simple!. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Online.10.18653/v1/2021.eacl-demos.31 ↗
45. Bianchi, F., Terragni, S., and Hovy, D. (2021, January 1–6). Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Online.10.18653/v1/2021.acl-short.96 ↗
46. Rahimi, H., Mimno, D., Hoover, J., Naacke, H., Constantin, C., and Amann, B. (2024, January 17–22). Contextualized Topic Coherence Metrics. Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024, St. Julian’s, Malta.10.18653/v1/2024.findings-eacl.123 ↗
47. Boehmer, N., Bredereck, R., and Peters, D. (2023, January 7–14). Rank aggregation using scoring rules. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i5.25685 ↗
48. Judging llm-as-a-judge with mt-bench and chatbot arena
49. Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N., Dhillon, I., Blistein, M., Ram, O., Zhang, D., and Rosen, E. (2025). Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv.
50. Ye, J., Wang, Y., Huang, Y., Chen, D., Zhang, Q., Moniz, N., Gao, T., Geyer, W., Huang, C., and Chen, P.Y. (2024). Justice or prejudice? quantifying biases in llm-as-a-judge. arXiv.
51. Li, D., Sun, R., Huang, Y., Zhong, M., Jiang, B., Han, J., Zhang, X., Wang, W., and Liu, H. (2025). Preference leakage: A contamination problem in llm-as-a-judge. arXiv.
52. Colombo, A., Bernasconi, A., Bellomarini, L., Guiso, L., Michelacci, C., and Ceri, S. (2025). LegisSearch: Navigating legislation with graphs and large language models. Artif. Intell. Law, 1–27.10.1007/s10506-025-09482-6 ↗