Two papers I co-authored have been accepted at the AI & Open Government Workshop (AIOG 2026), co-located with ICAIL 2026 in Singapore on June 8.
Both come out of student work at the ICAI OpenGov Lab, and tackle different sides of the same broad problem: automating parts of the FOIA process that are currently bottlenecked by manual review.
Out of the Box: Zero-Shot Vision-Language Models for Redaction Detection and Page-Stream Segmentation
Özgür Ateş, David Graus
This paper grew out of Özgür’s BSc AI individual project. He tested whether off-the-shelf vision-language models (Nanonets-OCR) without task-specific training can detect redactions in disclosed government documents and segment page-streams. Both are problems that come up when working with real FOIA releases, and both are surprisingly hard for OCR-based pipelines. We find that zero-shot VLMs do worse than task-specific trained supervised approaches, but perform well enough out of the box to be practically useful, which is good news for anyone who doesn’t have the resources or the labelled data to train custom models.
To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification
Maik Larooij, David Graus
Deliberative process privilege is one of the trickier FOIA exemption categories; whether something is exempt depends on context the classifier needs to reason about, not just surface features. This paper shows that a locally hosted LLM (Qwen 3.5) can classify deliberative process material with reasonable accuracy. The “local” part matters: government documents are often too sensitive to send to commercial LLM APIs in the first place, so a local model isn’t just nice-to-have, it’s frequently the only real option.
About AIOG
AIOG is a first-edition workshop bringing together researchers and practitioners across information retrieval, legal AI, NLP, e-discovery, and open government; communities that share concrete problems but rarely meet under one roof. I’m co-organizing alongside Graham McDonald (University of Glasgow) and Jason R. Baron (University of Maryland).
The full list of accepted papers is at aiog.net/accepted-papers. I’ll share the preprints here soon.
Big congratulations to Özgür and Maik!