AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction

• URL: http://arxiv.org/abs/2608.17184v1
• Date: Mon, 17 Aug 2026 22:48:01 GMT
• Title: AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction
• Abstract summary: This work aims to enable classification and quality scoring of incident narratives for existing and future reporting purposes.<n>The retrieval of historical accidents, reference imagery, and industry documents was benchmarked across embedding models.<n>Overall, this work provides a new framework rooted in local inferencing and text embedding models for future agentic applications.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the point of planning. A novel framework centered on large language models (LLMs) for highway construction safety reporting and planning is proposed as a foundation for future agentic applications, prioritizing deterministic, local inferencing. The first aim is to enable classification and quality scoring of incident narratives for existing and future reporting purposes. The second is to evaluate retrieval of relevant historical accidents, related imagery, and trusted industry documents for incorporation into daily safety plans. Neural probes were trained to classify incidents along four multiclass and two binary Occupational Injury and Illness Classification System (OIICS) fields and to derive an overall quality score, evaluated on a test set of over 15,000 narratives and a held-out set of 100 author-labeled records, benchmarked against a majority-vote LLM ensemble. The retrieval of historical accidents, reference imagery, and industry documents was benchmarked across embedding models using standard information retrieval metrics. OIICS classification reached 75% held-out accuracy, though the two binary flags were degenerate. The quality score, while meaningful on one database, was distorted on out-of-distribution fatalities in the held-out dataset. Accident retrieval recovered relevant incidents far above chance, performing best on lexically distinct construction activities. On document question answering, an open-weight decoder embedding model surpassed proprietary models. Overall, this work provides a new framework rooted in local inferencing and text embedding models for future agentic applications, with emphasis on bridging external data to JSA reports.

Related papers

• SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models [73.04773649437375]
  Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior.<n>We introduce SafeAtlas-VL, a dataset of 1.5M training instances that places image-, request-, and response-level judgments on a five-level ordered scale.<n>We also construct SafeAtlas-Bench, a set of 5,000 instances for evaluating five-level predictions and continuous risk scores.
  arXiv  Detail & Related papers  (2026-08-29T07:08:01Z)
• Assessing the Benefits of Combining Advanced Deep Learning Techniques for Post-Disaster Building Damage Assessment from UAV Imagery [3.016488960368601]
  We propose a hybrid framework that decouples detection from damage assessment.<n>A CV model first detects buildings and generates bounding boxes on the image that are then passed to an LVLM for damage classification and contextual interpretation.<n>We evaluate our framework on two real-world benchmarks: RescueNet and FloodNet.
  arXiv  Detail & Related papers  (2026-08-03T08:39:59Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models [66.75310318710073]
  We introduce textttHistoricalMisinfo, a curated dataset of $500$ contested events from $45$ countries.<n>To approximate real-world usage, we instantiate each event in $11$ prompt scenarios that reflect common communication settings.
  arXiv  Detail & Related papers  (2026-02-19T15:05:10Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• PentestJudge: Judging Agent Behavior Against Operational Requirements [0.0]
  PentestJudge is a system for evaluating operations of penetration testing agents.<n>We evaluate several models acting as judge agents, with the best model reaching an F1 score of 0.83.
  arXiv  Detail & Related papers  (2025-08-04T21:52:50Z)
• A new machine learning framework for occupational accidents forecasting with safety inspections integration [0.9562145896371785]
  We propose a generic framework for short-term occupational accident forecasting that leverages safety inspections and models accident occurrences as binary time series.<n>The proposed methodology converts routine safety inspection data into clear weekly risk scores, detecting the periods when accidents are most likely.
  arXiv  Detail & Related papers  (2025-06-30T09:28:11Z)
• Enhancing Traffic Accident Classifications: Application of NLP Methods for City Safety [41.76653295869846]
  We analyze traffic incidents in Munich to identify patterns and characteristics that distinguish different types of accidents.<n>The dataset consists of both structured tabular features, such as location, time, and weather conditions, as well as unstructured free-text descriptions detailing the circumstances of each accident.<n>To assess the reliability of labels, we apply NLP methods, including topic modeling and few-shot learning, which reveal inconsistencies in the labeling process.
  arXiv  Detail & Related papers  (2025-06-11T14:50:49Z)
• 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)
• AutoBencher: Towards Declarative Benchmark Construction [74.54640925146289]
  We use AutoBencher to create datasets for math, multilinguality, knowledge, and safety.<n>The scalability of AutoBencher allows it to test fine-grained categories knowledge, creating datasets that elicit 22% more model errors (i.e., difficulty) than existing benchmarks.
  arXiv  Detail & Related papers  (2024-07-11T10:03:47Z)
• Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses [76.59021017301127]
  We propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports. We further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes. Our experiments results show that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes.
  arXiv  Detail & Related papers  (2024-06-16T03:10:16Z)
• ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data [34.36975697486129]
  We present a rarely addressed task regarding semantic segmentation in accidental scenarios, along with an accident dataset DADA-seg. We propose a novel event-based multi-modal segmentation architecture ISSAFE. Our approach achieves +8.2% mIoU performance gain on the proposed evaluation set, exceeding more than 10 state-of-the-art segmentation methods.
  arXiv  Detail & Related papers  (2020-08-20T14:03:34Z)

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.