ASAIL 2026
8th Workshop on Automated Semantic Analysis of Information in Law
2026 June 12
Held online in conjunction with ICAIL 2026
Held online in conjunction with ICAIL 2026
Paper submission deadline: 2026/19/04 (AoE)
The Eighth Workshop on Automated Semantic Analysis of Information in Law (ASAIL 2026) will be held in conjunction with the 21st International Conference on Artificial Intelligence and Law (ICAIL 2026) at Singapore Management University, Singapore. ICAIL 2026 is scheduled for 8-12 June 2026.
ASAIL continues a successful workshop series associated with ICAIL, while expanding its remit in an important way. In 2026, the workshop moves from Automated Semantic Analysis of Information in Legal Texts to Automated Semantic Analysis of Information in Law.
This change reflects a broader understanding of how legal meaning is expressed, evidenced, contested, and processed. Legal information is not confined to written text. It also appears in images, diagrams, forms, tables, handwriting, audio recordings, hearings, oral testimony, video, and multimodal evidentiary bundles, often in combinations that must be interpreted together. ASAIL 2026 therefore invites work on the semantic understanding, extraction, representation, retrieval, alignment, and analysis of legal information across modalities.
The workshop aims to bring together researchers and practitioners from artificial intelligence and law, natural language processing, machine learning, computer vision, speech and audio processing, information retrieval, knowledge representation, HCI, socio-legal studies, and legal practice.
ASAIL 2026 welcomes original work on computational approaches to identifying and analysing meaning in legally relevant information, including but not limited to:
statutes, regulations, treaties, contracts, policies, and judicial decisions;
pleadings, submissions, witness statements, and evidentiary documents;
legislative debates, consultation materials, and policy records;
scanned records, forms, annotations, signatures, seals, and handwritten material;
photographs, diagrams, maps, and other visual legal artefacts;
courtroom, tribunal, police, administrative, and parliamentary audio or video;
multimodal case files combining text, image, audio, metadata, and structured records.
The workshop is especially interested in work that addresses how semantic content in law can be extracted or modelled from one or more modalities, and how such representations support legal reasoning, search, explanation, drafting, compliance, adjudication, or access to justice.
Topics include, but are not limited to:
Semantic analysis in legal language and documents
semantic parsing, information extraction, retrieval, classification, and summarisation for legal materials;
extraction of legal norms, obligations, permissions, powers, rights, and exceptions;
argument mining and rhetorical role analysis in judicial, legislative, and administrative materials;
fact extraction, event extraction, temporal reasoning, and precedent alignment;
multilingual and cross-jurisdictional semantic analysis of legal sources;
transformation of legal sources into formal, abstract, or structured representations.
Multimodal analysis of legal information
document AI for legal records, including OCR-rich, layout-aware, and form-aware methods;
semantic analysis of scanned filings, handwritten notes, evidentiary bundles, and archival materials;
interpretation of legally relevant images, diagrams, maps, and visual exhibits;
speech recognition, diarisation, and semantic analysis for hearings, testimony, interviews, or oral argument;
multimodal fusion across text, image, audio, and metadata in legal tasks;
grounding legal claims or evidentiary findings across heterogeneous sources.
AI methods for legal semantics
large language models, multimodal foundation models, retrieval-augmented systems, and agentic workflows;
domain adaptation, instruction tuning, and evaluation for legal semantic tasks;
neuro-symbolic approaches, knowledge graphs, ontologies, and structured representations for law;
explainability, uncertainty estimation, robustness, and error analysis in legal semantic systems;
human-AI collaboration and interface design for semantic legal analysis;
benchmark construction, annotation methodologies, and reproducible evaluation.
Applications and impact
access to justice, legal aid, and support for self-represented parties;
compliance, contract analytics, and policy monitoring;
legal research, case analysis, triage, and decision support;
judicial, administrative, and regulatory workflows;
fairness, accountability, transparency, privacy, and bias mitigation in legal AI;
responsible use of multimodal AI in legally sensitive or high-stakes settings.
We invite submissions in English describing original and unpublished work. Submissions must be formatted using the CEUR-WS single-column style and submitted through Microsoft CMT (https://cmt3.research.microsoft.com/ASAIL2026). Papers must be self-contained; the bibliography does not count toward the page limit, but appendices are not part of the workshop proceedings. Papers that exceed the page limit or fail to comply with the formatting requirements may be rejected without review.
Any paper under review for, or already accepted to, another archival venue should not be submitted to ASAIL for peer review.
Full research papers: 10 pages in the approved format, plus bibliography.
Full papers should present a substantial contribution to the state of the art. They should clearly motivate the legal problem, situate the work in prior literature, and provide sufficient detail on data, methods, results, and model behaviour. Strong submissions will go beyond reporting headline metrics and will discuss limitations, error patterns, generalisability, and legal relevance.
Short papers: 5-9 pages in the approved format, plus bibliography.
Short papers may report emerging work, position papers, novel tasks, negative results, resources, datasets, annotation schemes, interfaces, or early-stage multimodal research. They should still articulate a clear contribution and be likely to stimulate discussion at the workshop.
ASAIL 2026 will use a single-blind peer review process: submissions need not be anonymised, while reviewer identities remain anonymous to authors.
Submissions will be evaluated on:
relevance to the workshop theme;
originality and significance;
technical quality and methodological clarity;
adequacy of evaluation and analysis;
legal relevance and interdisciplinary value;
potential to generate fruitful discussion at the workshop.
ASAIL 2026 is intended as a full-day workshop with a strong discussion component, building on the successful format of thematic sessions followed by moderated author discussion.
Each session will be followed by a moderated discussion panel involving the presenters, with emphasis on shared challenges, reproducibility, evaluation, deployment, and future directions. The workshop’s goal is not only to present finished research, but also to cultivate an interdisciplinary community around semantic analysis in law in its full multimodal sense.
Submission deadline: 2026/04/19
Notification of acceptance: 2026/05/10
Camera-ready deadline: 2026/05/20
Workshop: June 2026, co-located with ICAIL 2026 at Singapore Management University, Singapore. ICAIL 2026 runs 8-12 June 2026.
ASAIL 2026 will be held in conjunction with ICAIL 2026 at Singapore Management University, Singapore. ICAIL 2026 is scheduled for 8-12 June 2026. The exact workshop day is to be confirmed.
At least one author of each accepted paper is expected to register for the workshop and present the work.
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.