{"type":"ScholarlyArticle","title":"Anti-Slavery Intelligence (ASI): An AI-Powered Tool for Modern Slavery Compliance Analysis and Remediation","authors":[{"name":"Mahmoud Gad","slug":"mahmoud-gad","given":"Mahmoud","family":"Gad","affiliation":"Lancaster University Management School , UK"},{"name":"Abdessalam Elhabbash","slug":"abdessalam-elhabbash","given":"Abdessalam","family":"Elhabbash","affiliation":"Lancaster University Management School , UK"},{"name":"Steven Young","slug":"steven-young","given":"Steven","family":"Young","affiliation":"Lancaster University Management School , UK"}],"abstract":"We present Anti-Slavery Intelligence (ASI), a deployed AI system that analyses corporate modern slavery statements to identify compliance gaps and generate prioritised remediation advice. ASI orchestrates a multi-model pipeline: Gemini-2.5-Flash for vision-enhanced PDF parsing and structured compliance scoring against 48 expert-defined criteria, and Gemini-2.5-Pro for synthesising company-specific, timeline-based recommendations. A benchmarking engine compares each statement against industry and FTSE index averages across 11 sectors. Evaluation on 95 expert-annotated statements yields an F1-score of 0.86 and recall of 0.94, reducing time to generate an initial compliance assessment from several hours to approximately five minutes per document. ASI is publicly available at https://www.antislaveryintelligence.co.uk/ with free access for academics and NGOs. A demonstration video is at https://youtu.be/DNhdEGrRwzg.","doi":"10.24963/ijcai.2026/964","url":"https://ijcai.org/proceedings/2026/964","pdf":"https://ijcai.org/proceedings/2026/0964.pdf","markdown":"https://ijcai.org/proceedings/2026/964.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/964","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Demo Track","track":"Demo Track","number":964,"pages":{"first":8393,"last":8396},"keywords":["AI: Multidisciplinary Topics and Applications","AI: Natural Language Processing","AI: Humans and AI"],"videos":[],"references":[{"position":1,"raw":"[ILO et al., 2022] ILO, Walk Free, and IOM. Global Es- timates of Modern Slavery: Forced Labour and Forced Marriage. International Labour Organization, Geneva. https://doi.org/10.54394/CHUI5986, 2022.","title":"ILO, Walk Free, and IOM. Global Estimates of Modern Slavery: Forced Labour and Forced Marriage","authors":"Ilo","year":"2022","venue":null,"doi":"10.54394/chui5986","url":"https://doi.org/10.54394/CHUI5986,2022","internal_url":null},{"position":2,"raw":"[UK Government, 2015] UK Government. Modern Slav- ery Act 2015, Section 54: Transparency in Supply Chains. https://www.legislation.gov.uk/ukpga/2015/30/ section/54, 2015.","title":"UK Government. Modern Slavery Act 2015","authors":null,"year":"2015","venue":"Transparency in Supply Chains","doi":null,"url":"https://www.legislation.gov.uk/ukpga/2015/30/section/54,2015","internal_url":null},{"position":3,"raw":"[CCLA, 2024] CCLA Investment Management. Find it, Fix it, Prevent it: Modern Slavery Report 2024. https://www.ccla.co.uk/sites/default/files/2024-10/","title":"CCLA Investment Management. Find it, Fix it","authors":"Ccla","year":"2024","venue":"Prevent it: Modern Slavery Report 2024","doi":null,"url":"https://www.ccla.co.uk/sites/default/files/2024-10/","internal_url":null},{"position":4,"raw":"[Nersessian and Pachamanova, 2022] David Nersessian and Dessislava Pachamanova. Human trafficking in the global supply chain: Using machine learning to understand cor- porate disclosures under the UK Modern Slavery Act. Harvard Human Rights Journal, 35:515-535, 2022.","title":"Human trafficking in the global supply chain: Using machine learning to understand corporate disclosures under the UK Modern Slavery Act","authors":"Pachamanova Nersessian, David Nersessian, Dessislava Pachamanova","year":"2022","venue":"Harvard Human Rights Journal","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Mai et al., 2023] Nam Mai, Petros Vourvachis, and Suzana Grubnic. The impact of the UK's Modern Slavery Act (2015) on the disclosure of FTSE 100 companies. The British Accounting Review, 55(3):101115, 2023. https:// doi.org/10.1016/j.bar.2022.101115.","title":"Nam Mai, Petros Vourvachis, and Suzana Grubnic. The impact of the UK's Modern Slavery Act (2015) on the disclosure of FTSE 100 companies","authors":"Mai","year":"2023","venue":"The British Accounting Review","doi":"10.1016/j.bar.2022.101115","url":"https://doi.org/10.1016/j.bar.2022.101115","internal_url":null},{"position":6,"raw":"[BHRRC, 2016] Business & Human Rights Resource Cen- tre. FTSE 100 At the Starting Line: An Analysis of Company Statements Under the UK Modern Slavery Act. BHRRC, London, 2016.","title":"Business & Human Rights Resource Centre. FTSE 100 At the Starting Line: An Analysis of Company Statements Under the UK Modern Slavery Act","authors":"Bhrrc","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Poon et al., 2025] Ser-Huang Poon, Eghbal Rahimikia, Philip Jobi Vallavanthra, and Siliang Wei. Analysing mod- ern slavery statements using large language models. In Handbook of Artificial Intelligence in Higher Education, chapter 9, pages 134-151.","title":"Analysing modern slavery statements using large language models","authors":"Poon","year":"2025","venue":"Handbook of Artificial Intelligence in Higher Education","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Bora et al., 2025] Adriana Eufrosina Bora, Akshatha Arodi, Duoyi Zhang, Jordan Bannister, Mirko Bronzi, Arsene Fansi Tchango, Md Abul Bashar, Richi Nayak, and Ker- rie Mengersen. AIMSCheck: Leveraging LLMs for AI- assisted review of modern slavery statements across ju- risdictions. In Proceedings of the 63rd Annual Meet- ing of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 9109-9135, 2025. https: //aclanthology.org/2025.acl-long.446/.","title":"AIMSCheck: Leveraging LLMs for AIassisted review of modern slavery statements across jurisdictions","authors":"Adriana Eufrosina Bora, Akshatha Arodi, Duoyi Zhang, Jordan Bannister, Mirko Bronzi, Arsene Fansi Tchango, Md Abul Bashar, Richi Nayak, Kerrie Mengersen","year":"2025","venue":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics","doi":null,"url":"https://aclanthology.org/2025.acl-long.446/","internal_url":null},{"position":9,"raw":"[TISCreport, 2024] TISCreport. Modern Slavery Act State- ment AI Audit. https://tiscreport.org/products/service/ modern-slavery-act-statement-ai-audit, 2024.","title":"TISCreport. Modern Slavery Act Statement AI Audit","authors":"Tiscreport","year":"2024","venue":null,"doi":null,"url":"https://tiscreport.org/products/service/modern-slavery-act-statement-ai-audit,2024","internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}