Generative AI for FFRDCs

• URL: http://arxiv.org/abs/2509.21040v1
• Date: Thu, 25 Sep 2025 11:45:39 GMT
• Title: Generative AI for FFRDCs
• Abstract summary: We show how large language models can accelerate summarization, classification, extraction, and sense-making with only a few input-output examples.<n>To enable use in sensitive government contexts, we apply OnPrem$.$LLM, an open-source framework for secure and flexible application of generative AI.
• Score: 2.132096006921048
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federally funded research and development centers (FFRDCs) face text-heavy workloads, from policy documents to scientific and engineering papers, that are slow to analyze manually. We show how large language models can accelerate summarization, classification, extraction, and sense-making with only a few input-output examples. To enable use in sensitive government contexts, we apply OnPrem$.$LLM, an open-source framework for secure and flexible application of generative AI. Case studies on defense policy documents and scientific corpora, including the National Defense Authorization Act (NDAA) and National Science Foundation (NSF) Awards, demonstrate how this approach enhances oversight and strategic analysis while maintaining auditability and data sovereignty.

Related papers

• Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review [48.61205783234013]
  PaperGuard is the first comprehensive benchmark designed to evaluate and defend AI-generated peer-review against domain-specific, cross-modal attacks.<n>Our framework is built on three pillars: (1) a new multimodal peer-review dataset spanning multiple scientific domains; (2) a unified suite of attacks, including black-box prompt injections and white-box perturbations; and (3) a practical defense, motivated by the long-term challenge of academic papers, that uses chunk-based embedding search to efficiently localize and mitigate harmful instructions.
  arXiv  Detail & Related papers  (2026-06-10T22:06:35Z)
• The Creation and Analysis of Government AI Transparency Statements in Australia [13.317344301057219]
  Australia's Standard for AI Transparency Statements (AITS) requires government bodies to disclose how AI is used in practice.<n>This paper presents the first government AITS dataset, dubbed AITS-101, and provides the first systematic analysis of their content.
  arXiv  Detail & Related papers  (2026-04-28T19:34:41Z)
• Inspectable AI for Science: A Research Object Approach to Generative AI Governance [35.790980610679384]
  This paper introduces AI as a Research Object (AI-RO)<n>Instead of debating whether AI is an author or merely a tool, we propose treating AI interactions as structured, inspectable components of the research process.
  arXiv  Detail & Related papers  (2026-04-13T10:13:20Z)
• Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance [0.0]
  This paper presents a citation-enforced RAG framework for fiscal document intelligence that prioritises explainability and auditability.<n> Evaluation on real IRS and state tax documents demonstrates improved citation fidelity, reduced provenance, and analyst-usable explanations.
  arXiv  Detail & Related papers  (2026-03-11T20:01:35Z)
• AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research [85.51475655916026]
  AgentCPM-Report is a lightweight yet high-performing local solution composed of a framework that mirrors the human writing process.<n>Our framework uses a Writing As Reasoning Policy (WARP), which enables models to dynamically revise outlines.<n>Experiments on DeepResearch Bench, DeepConsult, and DeepResearch Gym demonstrate that AgentCPM-Report outperforms leading closed-source systems.
  arXiv  Detail & Related papers  (2026-02-06T09:45:04Z)
• A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy [0.5958527024442727]
  This work presents the first systematic literature review on prompt injection mitigation strategies.<n>It identifies studies beyond those documented in NIST's report and other academic reviews and surveys.<n>By adopting NIST's established terminology and taxonomy as a foundation, we promote consistency and enable future researchers to build upon the standardized taxonomy proposed in this work.
  arXiv  Detail & Related papers  (2026-01-29T19:08:37Z)
• Let the Barbarians In: How AI Can Accelerate Systems Performance Research [80.43506848683633]
  We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems.<n>We demonstrate that ADRS-generated solutions can match or even outperform human state-of-the-art designs.
  arXiv  Detail & Related papers  (2025-12-16T18:51:23Z)
• A Comparative Study of Retrieval Methods in Azure AI Search [4.799746336710645]
  This study evaluates retrieval strategies within Microsoft Azure's Retrieval-Augmented Generation framework.<n>We compare the performance of Azure AI Search's keyword, semantic, vector, hybrid, and hybrid-semantic retrieval methods.
  arXiv  Detail & Related papers  (2025-12-08T22:20:02Z)
• The Journal of Prompt-Engineered Philosophy Or: How I Started to Track AI Assistance and Stopped Worrying About Slop [0.0]
  Article analyzes how incentives discourage transparency in precisely the work where it matters most.<n>Traditional venues cannot resolve this tension through policy tweaks alone, as the underlying prestige economy rewards opacity.<n>It proposes an alternative publishing infrastructure: a venue outside prestige systems that enforces mandatory disclosure, enables reproduction-based review, and supports ecological validity through detailed documentation.
  arXiv  Detail & Related papers  (2025-11-10T08:56:21Z)
• How Can AI Augment Access to Justice? Public Defenders' Perspectives on AI Adoption [6.949832807566659]
  We find that AI adoption is constrained by costs, restrictive office norms, confidentiality risks, and unsatisfactory tool quality.<n>Public defenders view AI as most useful for evidence investigation to analyze overwhelming amounts of digital records.<n>Courtroom representation and defense strategy are considered least compatible with AI assistance.
  arXiv  Detail & Related papers  (2025-10-27T02:26:08Z)
• ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search [69.60882125603133]
  We present ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents.<n>Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.
  arXiv  Detail & Related papers  (2025-09-27T22:36:42Z)
• Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training [67.895981259683]
  General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence.<n>Current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools.<n>We present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework.
  arXiv  Detail & Related papers  (2025-08-01T08:11:31Z)
• The AI Imperative: Scaling High-Quality Peer Review in Machine Learning [49.87236114682497]
  We argue that AI-assisted peer review must become an urgent research and infrastructure priority.<n>We propose specific roles for AI in enhancing factual verification, guiding reviewer performance, assisting authors in quality improvement, and supporting ACs in decision-making.
  arXiv  Detail & Related papers  (2025-06-09T18:37:14Z)
• Harnessing AI for efficient analysis of complex policy documents: a case study of Executive Order 14110 [44.99833362998488]
  Policy documents, such as legislation, regulations, and executive orders, are crucial in shaping society. This study aims to evaluate the potential of AI in streamlining policy analysis and to identify the strengths and limitations of current AI approaches.
  arXiv  Detail & Related papers  (2024-06-10T11:19:28Z)
• INACIA: Integrating Large Language Models in Brazilian Audit Courts: Opportunities and Challenges [7.366861473623427]
  INACIA is a groundbreaking system designed to integrate Large Language Models (LLMs) into the operational framework of Brazilian Federal Court of Accounts (TCU) We demonstrate INACIA's potential in extracting relevant information from case documents, evaluating its legal plausibility, and formulating propositions for judicial decision-making.
  arXiv  Detail & Related papers  (2024-01-10T17:13:28Z)
• Entity Graph Extraction from Legal Acts -- a Prototype for a Use Case in Policy Design Analysis [52.77024349608834]
  This paper presents a prototype developed to serve the quantitative study of public policy design. Our system aims to automate the process of gathering legal documents, annotating them with Institutional Grammar, and using hypergraphs to analyse inter-relations between crucial entities.
  arXiv  Detail & Related papers  (2022-09-02T10:57:47Z)
• MAIR: Framework for mining relationships between research articles, strategies, and regulations in the field of explainable artificial intelligence [2.280298858971133]
  It is essential to understand the dynamics of the impact of regulation on research papers and AI-related policies. This paper introduces a novel framework for joint analysis of AI-related policy documents and XAI research papers.
  arXiv  Detail & Related papers  (2021-07-29T20:41:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.