SURGeLLM 2026 Structured Understanding, Retrieval, and Generation in the LLM Era
SURGeLLM is a workshop at ACL 2026 bringing together NLP, IR, data management, and visualization researchers to advance structure-aware understanding, retrieval, generation, and evaluation.
At a Glance
Why submit?
Structured artifacts are everywhere — but today’s LLM systems still struggle with faithful reasoning, retrieval, and generation over them.
- Get feedback from a cross-community audience (NLP × IR × DB × Visualization).
- Publish archival papers (proceedings) or present non-archival work (discussion-only).
- Bring new benchmarks, systems, datasets, and lessons learned — including negative results.
Who should submit?
We welcome work from students, researchers, and practitioners.
- Table QA, Text-to-SQL, schema linking, structured retrieval, chart/map/diagram understanding.
- Evaluation, robustness, faithfulness, interpretability, and structure-aware agents.
- Applications in enterprise data, science, healthcare, finance, and more.
Workshop format
A full-day workshop with invited talks and community interaction.
- Invited talks + panel discussion.
- Contributed oral presentations and poster session.
- Student mentoring lunch session (planned).
Topics
- Methods for tabular understanding and question answering (multi-table reasoning, multi-hop inference, and multimodal integration).
- Natural language interfaces to structured data (Text-to-SQL, semantic parsing, schema linking, and data discovery).
- Structure-aware retrieval (tables, cells/rows, chart elements, maps, workflows, and code fragments).
- Structured generation (text → tables/charts/figures/code) with faithfulness, controllability, and robust evaluation.
- Agentic systems for structured data understanding and analysis (time series, graphs, tabular, etc).
- Data-centric AI for LLMs on structured data (representation learning, augmentation, robustness, and domain adaptation).
- Benchmarking and evaluation (scalability, throughput, contamination, reproducibility, and human-centered assessment).
- Applications and governance for LLMs over structured data (DataOps, privacy, fairness, and reliability).
Important Dates
All datesNext key deadline
days left
| Direct paper submission deadline | |
|---|---|
| Pre-reviewed ARR commitment deadline | |
| Notification of acceptance | |
| Camera-ready paper due | |
| Workshop dates | – |
All deadlines are end-of-day in Anywhere on Earth (AoE).
Add to calendar.
Invited Speakers
All speakers
Lisa Amini
confirmed
Leads IBM’s Data & AI Platforms Research; works on infusing generative and agentic AI into enterprise data platforms.
Dan Roth
confirmed
Eduardo D. Glandt Distinguished Professor at UPenn; Chief AI Scientist at Oracle; Fellow of AAAS/ACM/AAAI/ACL.
Heng Ji
confirmed
Professor at UIUC; Co-founder/CTO of Medicas AI; Founding Director of AICE/ASKS; ACL Fellow.
Hamid Palangi
confirmed
Staff Research Scientist at Google; Affiliate Associate Professor at UW.
About
SURGeLLM brings together researchers and practitioners across NLP, information retrieval, data management, and visualization to make structured artifacts (tables, charts, maps, flowcharts, and diagrams) first-class citizens in modern LLM systems — across understanding, retrieval, generation, and evaluation.
- Structured understanding: robust reasoning and attribution over tables, databases, and other structured artifacts.
- Structured retrieval: structure-aware retrieval for tables/cells, charts, maps, workflows, and code.
- Structured generation: text → SQL/table/chart/code with faithfulness, controllability, and reliable evaluation.
- LLMs + structured data: data-centric methods, benchmarks, and real-world deployments with governance.
- Community: invited talks, posters, a panel, and a student mentoring lunch session.
We encourage submissions from students and underrepresented communities, and welcome well-supported negative results and lessons learned.
Questions: surgellm@googlegroups.com.
Updates
All updatesNo updates yet.
Help spread the word: promotion kit.