Legal Ai For All: Reducing Perplexity And Boosting Accuracy In Normative Texts With Fine-Tuned Llms And Rag

Skip to main Communities My dashboard Log in Sign up Published April 13, 2026 | Version v1 Journal article Open Legal Ai For All: Reducing Perplexity And Boosting Accuracy In Normative Texts With Fine-Tuned Llms And Rag Authors/Creators CH.VENKATA GOPI, M. VENKATA NARENDRA BABU, A. DEVENDRA, BANDLA.KARTHIK, Mrs. N. RADHA Description Abstract Legal texts are often written in highly technical and formal language, making them difficult for non-experts to understand and interpret correctly. With the growing adoption of artificial intelligence in the legal domain, large language models (LLMs) have shown promise in supporting natural language interaction with normative and regulatory documents. However, general-purpose LLMs frequently suffer from high perplexity, hallucinations, and limited domain reliability when applied to legal texts, which restricts their practical usability in real-world legal information systems. To address these challenges, this paper proposes a reliable and enhanced legal text interpretation framework that combines fine-grained large language models with Retrieval-Augmented Generation (RAG). The approach leverages supervised fine-tuning on a synthetic yet human-validated legal question–answer dataset derived from official data protection laws and regulations, enabling clause-level and article-level understanding of legal content. In addition, a RAG architecture is integrated to ground model responses in authoritative legal sources, thereby reducing hallucinations and improving factual consistency while maintaining adaptability to evolving legal documents. Experimental results demonstrate that the proposed framework significantly improves legal question-answering performance compared to baseline models. Fine-tuned models achieve substantial reductions in perplexity, while the RAG-enhanced system attains accuracy levels exceeding 90% across multiple difficulty categories in benchmark evaluations. These findings highlight that combining fine-grained model adaptation with retrievalgrounded generation provides a robust and scalable solution for reliable legal text interpretation, supporting broader accessibility and trustworthy use of AI-driven legal information systems. Keywords Large language models (LLM), generative AI, fine tuning, RAG, Ecuadorian law, legal. Files Legal Ai For All Reducing Perplexity And Boosting Accuracy In Normative Texts With Fine-Tuned Llms And Rag.pdf Files (267.5 kB) Name Size Download all Legal Ai For All Reducing Perplexity And Boosting Accuracy In Normative Texts With Fine-Tuned Llms And Rag.pdf md5:a11ca4abd32b8d72def10f2e2eb9b77f 267.5 kB Preview Download 44 Views 22 Downloads Show more details All versions This version Views Total views 44 44 Downloads Total downloads 22 22 Data volume Total data volume 5.9 MB 5.9 MB More info on how stats are collected.... Versions External resources Indexed in OpenAIRE Communities Details DOI DOI Badge DOI 10.5281/zenodo.19554070 Markdown [](https://doi.org/10.5281/zenodo.19554070) reStructuredText .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.19554070.svg :target: https://doi.org/10.5281/zenodo.19554070 HTML <a href="https://doi.org/10.5281/zenodo.19554070"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.19554070.svg" alt="DOI"></a> Image URL https://zenodo.org/badge/DOI/10.5281/zenodo.19554070.svg Target URL https://doi.org/10.5281/zenodo.19554070 Resource type Journal article Publisher Zenodo Rights License Creative Commons Attribution 4.0 International The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited. Read more Citation Export Technical metadata Created April 13, 2026 Modified April 13, 2026 Jump up About About Policies Infrastructure Principles Projects Roadmap Contact Blog Blog Support Help FAQ Developers REST API OAI-PMH Contribute GitHub Donate Funded by Powered by CERN Data Centre & InvenioRDM Status Privacy policy Cookie policy Terms of Use This site uses cookies. Find out more on how we use cookies Accept all cookies Accept only essential cookies

Related documents

• Leveraging LLM agents and knowledge models for automated legal reasoning#1178520
• Building Legal Literacies for Text Data Mining#452150
• AI Literacy for Legal AI Systems: a Practical Approach#1178614
• Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization#124088
• An English version of legal maxims : with the original forms, alphabetically arranged, and an index of subjects#334135