arXiv Computation and Language August 25, 2026 By Hung Nguyen, Jaehoon Lee, Namgyun Kim, Kuan-Hao Huang

ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives

Read the original on arXiv Computation and Language →

ConstructCIE is a manually annotated dataset designed for extracting causal information from OSHA construction accident reports. It employs a hierarchical schema that categorizes accident types, causal factors, sub‑causal factors, and the supporting evidence spans. Experiments with supervised sequence taggers and instruction‑tuned large language models show strong performance on accident‑type prediction and broad causal recovery, yet precise span‑level extraction remains challenging, highlighting the need for better domain grounding and evidence extraction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

llms

arXiv Machine Learning

2d ago

A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis

arXiv:2610.35658v1 Announce Type: new Abstract: Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on thes...

By Yutian Pang, Yifang Tian, Jiacheng Xie, Xinyu Zhao, Jueming Hu, John-Paul Clarke, Hans-Arno Jacobsen

llms safety

arXiv Machine Learning

Jun 10

LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems

arXiv:2606. 09892v1 Announce Type: new Abstract: Textual event records, such as alarm logs, have become an increasingly common data source in engineering and manufacturing systems.

By Xiaofeng Xiao, Jianhong Chen, Qiuzhuang Sun, Naichen Shi, Xubo Yue

llms

Hugging Face Trending Papers

Aug 5

Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study

Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes.

llms fine-tuning

arXiv Computation and Language

Sep 24

Structuring occupational accident narratives for cross-sector safety analysis: Transferability of accident-process role classification

The study investigates whether a model trained on construction‑sector occupational accident narratives can accurately classify accident‑process roles in other sectors and reporting environments. Using 42,244 factual units from 6,040 construction narratives, the authors compared TF‑IDF, frozen pretrained representations, and task‑adapted pretrained models, achieving up to 85.7% balanced accuracy without retraining. The models performed consistently across metallurgy, chemistry‑plastics, and an independent company corpus, though performance varied more on the latter due to differing reporting practices.

By Aho Yapi, Pierre Latouche, Arnaud Guillin, Yan Bailly

safety

arXiv AI

Sep 2

Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources

The paper introduces a pipeline that merges structured disaster records from EM‑DAT with unstructured documents from ReliefWeb and the European Media Monitor to generate source‑grounded disaster storylines and causal knowledge graphs. Using Retrieval‑Augmented Generation, it produces tabular event profiles covering 17 fields and builds causal graphs enriched with citation‑grounded explanatory narratives, allowing traceability to primary sources. Human evaluation across three crisis cases shows high retrieval precision, strong faithfulness of causal relations, and a clear expert preference for citation‑grounded components over ungrounded ones.

By Ivan Decostanzi, Michele Ronco, Sergio Consoli, Christina Corbane, Lorenzo Bertolini, Indaco Biazzo, Daria Mihaila, Manuel Garcia-Herranz, Felix Schwebel, Yelena Mejova, Kyriaki Kalimeri

rag

arXiv Computation and Language

Sep 25

ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints

ARGUS is a pipeline that builds document-level Event Knowledge Graphs (EKGs) from U.S. employment‑discrimination complaints. It uses a 5W1H-inspired schema, legal-domain models, and LLM‑based structured generation to extract fact‑bearing statements, create chunk‑level event graphs with participant, temporal, and causal structure, and merge them into comprehensive document representations. Evaluation shows that graph‑structured classifiers outperform raw and linearized baselines on claim classification, and EKG‑only retrieval improves document‑scoped QA, though overall open‑retrieval gains are limited by low first‑stage candidate recall.

By Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi, Leslie Barrett, Madhavan Seshadri, Enrico Santus

llms rag