Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data

[2503.10676] Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2503.10676 (cs) [Submitted on 10 Mar 2025 ( v1 ), last revised 13 Apr 2026 (this version, v2)] Title: Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data Authors: Swati Rallapalli , Shannon Gallagher , Andrew O. Mellinger , Jasmine Ratchford , Anusha Sinha , Tyler Brooks , William R. Nichols , Nick Winski , Bryan Brown View a PDF of the paper titled Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data, by Swati Rallapalli and 8 other authors View PDF HTML (experimental) Abstract: We study the efficacy of fine-tuning Large Language Models (LLMs) for the specific task of report (government archives, news, intelligence reports) summarization. While this topic is being very actively researched - our specific application set-up faces two challenges: (i) ground-truth summaries maybe unavailable (e.g., for government archives), and (ii) availability of limited compute power - the sensitive nature of the application requires that computation is performed on-premise and for most of our experiments we use one or two A100 GPU cards. Under this set-up we conduct experiments to answer the following questions. First, given that fine-tuning the LLMs can be resource intensive, is it feasible to fine-tune them for improved report summarization capabilities on-premise? Second, what are the metrics we could leverage to assess the quality of these summaries? We conduct experiments on two different fine-tuning approaches in parallel and our findings reveal interesting trends regarding the utility of fine-tuning LLMs. Specifically, we find that in many cases, fine-tuning helps improve summary quality and in other cases it helps by reducing the number of invalid or garbage summaries. Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2503.10676 [cs.CL] (or arXiv:2503.10676v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2503.10676 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Swati Rallapalli [ view email ] [v1] Mon, 10 Mar 2025 23:47:11 UTC (129 KB) [v2] Mon, 13 Apr 2026 20:22:50 UTC (90 KB) Full-text links: Access Paper: View a PDF of the paper titled Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data, by Swati Rallapalli and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-03 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation#1037286
• OSCAR: Order-aware Scoring and Calibration for AI Rankings#1050313
• LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking#609791
• Position: A Score Should Travel With Its Repair History#1180130
• Position: A Score Should Travel With Its Repair History#1180035