SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings

• URL: http://arxiv.org/abs/2606.12897v1
• Date: Thu, 11 Jun 2026 04:55:37 GMT
• Title: SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings
• Abstract summary: Retrieval-augmented generation (RAG) systems that rely on free-form rewriting can introduce hallucinations and unstable trade-offs between completeness and conciseness.<n>We compare strategies that balance precision, recall and safety across document types and model scales.<n>Experiments are conducted on documents of varying length and structure, including local NHS acute care and oncology guidelines and UK-wide NICE guidelines.
• Score: 2.7975477743127346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly used to access organisational documentation, including standard operating procedures (SOPs), HR policies and institutional guidelines. However, retrieval-augmented generation (RAG) systems that rely on free-form rewriting can introduce hallucinations and unstable trade-offs between completeness and conciseness, particularly in safety- and compliance-critical settings. Objectives: To evaluate extraction as a hallucination-resistant alternative to rewriting-based RAG and compare strategies that balance precision, recall and safety across document types and model scales. Methods: We compare multiple prompting strategies, including line-number-based source selection, extraction of relevant guideline sentences with explicit safety annotations, and a multi-stage pipeline that refines draft answers using supporting evidence from source guidelines. Experiments are conducted on documents of varying length and structure, including local NHS acute care and oncology guidelines and UK-wide NICE guidelines, using both frontier-scale and locally deployable models. Performance is assessed using automatic metrics and human expert evaluation of relevance and completeness. Results: Line-number selection achieves the strongest results, outperforming direct copying and safety-focused strategies across both large and small models while maintaining high term recall (up to 95%) and close alignment with source text. Safety-oriented approaches improve precision but introduce systematic omissions, while multi-stage filtering further amplifies this trade-off. Performance varies with document structure: line-based extraction excels in protocol-like content, whereas alternative strategies perform better on more verbose documents (up to 97% term recall).

Related papers

• DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods [2.0789144738685956]
  This paper introduces DECODEM, a set of benchmark datasets for evaluating the automated extraction of corporate governance variables from organizational documents.<n>The benchmarks pair randomly sampled corporate charters and bylaws with high-quality human annotations covering a range of governance provisions commonly studied in empirical work.<n>The results show that automated extraction is feasible at a high level of accuracy for many provisions, with median performance near the upper bound across approaches.
  arXiv  Detail & Related papers  (2026-07-17T11:48:31Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow.<n>We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• Adaptive Chunking: Optimizing Chunking-Method Selection for RAG [0.0]
  We introduce Adaptive Chunking, a framework that selects the most suitable chunking strategy for each document.<n>On a diverse corpus spanning legal, technical, and social science domains, our metric-merge adaptive method significantly improves downstream RAG performance.
  arXiv  Detail & Related papers  (2026-03-26T11:20:52Z)
• Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents [0.0]
  Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs)<n>This paper presents an empirical study quantifying performance differences across four chunking strategies.
  arXiv  Detail & Related papers  (2026-03-25T17:35:24Z)
• Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation [57.97548022208733]
  We show that seemingly superficial choices in key-value extraction can induce shifts in accuracy and stability.<n>We introduce Contextual Normalization, a strategy that adaptively standardizes context representations before generation.
  arXiv  Detail & Related papers  (2025-10-15T06:28:25Z)
• Just-in-time Episodic Feedback Hinter: Leveraging Offline Knowledge to Improve LLM Agents Adaptation [77.90555621662345]
  We present JEF Hinter, an agentic system that distills offline traces into compact, context-aware hints.<n>A zooming mechanism highlights decisive steps in long trajectories, capturing both strategies and pitfalls.<n>Experiments on MiniWoB++, WorkArena-L1, and WebArena-Lite show that JEF Hinter consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-05T21:34:42Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Exploring Information Retrieval Landscapes: An Investigation of a Novel Evaluation Techniques and Comparative Document Splitting Methods [0.0]
  In this study, the structured nature of textbooks, the conciseness of articles, and the narrative complexity of novels are shown to require distinct retrieval strategies. A novel evaluation technique is introduced, utilizing an open-source model to generate a comprehensive dataset of question-and-answer pairs. The evaluation employs weighted scoring metrics, including SequenceMatcher, BLEU, METEOR, and BERT Score, to assess the system's accuracy and relevance.
  arXiv  Detail & Related papers  (2024-09-13T02:08:47Z)
• Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation [60.493180081319785]
  We propose a systematic way to estimate the capacity of a truncation sampling method by considering the trade-off between diversity and risk at each decoding step.<n>Our work offers a comprehensive comparison of existing truncation sampling methods and serves as a practical user guideline for their parameter selection.
  arXiv  Detail & Related papers  (2024-08-24T14:14:32Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [66.93260816493553]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios.<n>With a focus on factual accuracy, we propose three novel metrics: Completeness, Hallucination, and Irrelevance.<n> Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)

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.