---
title: "Workshop on Structured Understanding, Retrieval, and"
description: "Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026 — accepted papers: 14 papers in the Elamur…"
canonical: "https://research.elamur.ai/free/en/venues/surgellm/2026/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/surgellm/2026/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Workshop on Structured Understanding…](https://md.research.elamur.ai/free/en/venues/surgellm/) / 2026

# Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026 — accepted papers

Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era 2026 is the 2026 edition of the Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era, held in San Diego, California, United States, July 2026 (publisher: Association for Computational Linguistics). The ACL Anthology lists 24 papers of it; our library holds 14 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

📍 San Diego, California, [United States](https://md.research.elamur.ai/free/en/countries/united-states/) · 🗓 July 2026

[**24** papers in the proceedings](#all) · [**14** works in our library](https://md.research.elamur.ai/free/en/venues/surgellm/2026/#works) · [**8** citations of these works](https://md.research.elamur.ai/free/en/venues/surgellm/2026/#works)

## Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. **[More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval](https://md.research.elamur.ai/free/en/papers/zuo-2026-more-than-efficiency-embedding-compression/)**Chunsheng Zuo, Daniel Khashabi*2 citations · our summary*
2. **[Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs ↗](https://aclanthology.org/2026.surgellm-1.8/)**Felix Fricke, Simon Malberg, Georg Groh*1 citation*
3. **[StructHallu-Drift: Benchmarking Structured Hallucinations Under Schema Evolution in LLMs ↗](https://aclanthology.org/2026.surgellm-1.22/)**Mujtaba Hasan*1 citation*
4. **[The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs](https://md.research.elamur.ai/free/en/papers/tahan-2026-mighty-torr-benchmark-table-reasoning/)**Shir Ashury-Tahan, Yifan Mai, Rajmohan C et al.*1 citation · our summary*
5. **[TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://md.research.elamur.ai/free/en/papers/zeng-2026-treediff-ast-guided-code-generation/)**Yiming Zeng, Jinghan Cao, Zexin Li et al.*1 citation · our summary*

## All accepted papers (24)

The most cited first; 14 with our summary link to their page here, the others to the original.

1. **[More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval](https://md.research.elamur.ai/free/en/papers/zuo-2026-more-than-efficiency-embedding-compression/)**Chunsheng Zuo, Daniel Khashabi*2 citations · our summary*
2. **[Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs ↗](https://aclanthology.org/2026.surgellm-1.8/)**Felix Fricke, Simon Malberg, Georg Groh*1 citation*
3. **[StructHallu-Drift: Benchmarking Structured Hallucinations Under Schema Evolution in LLMs ↗](https://aclanthology.org/2026.surgellm-1.22/)**Mujtaba Hasan*1 citation*
4. **[The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs](https://md.research.elamur.ai/free/en/papers/tahan-2026-mighty-torr-benchmark-table-reasoning/)**Shir Ashury-Tahan, Yifan Mai, Rajmohan C et al.*1 citation · our summary*
5. **[TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://md.research.elamur.ai/free/en/papers/zeng-2026-treediff-ast-guided-code-generation/)**Yiming Zeng, Jinghan Cao, Zexin Li et al.*1 citation · our summary*
6. **[Asking language models how to represent data for fine-tuning](https://md.research.elamur.ai/free/en/papers/singh-2026-asking-language-models-how-represent/)**Usneek Singh, Ananya Singha, Abhijeet Awasthi et al.*our summary*
7. **[Can LLMs Self-Correct Table Reasoning Errors?](https://md.research.elamur.ai/free/en/papers/shaikh-2026-can-llms-self-correct-table/)**Farseen Shaikh*our summary*
8. **[Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards](https://md.research.elamur.ai/free/en/papers/zhang-2026-chart-rl-generalized-chart-comprehension/)**Xin Zhang, Xingyu Li, Rongguang Wang et al.*our summary*
9. **[DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents](https://md.research.elamur.ai/free/en/papers/wang-2026-dsmentor-curriculum-guided-inference-online/)**He Wang, Alexander Hanbo Li, Yiqun Hu et al.*our summary*
10. **[Generalization in Graph Reasoning: A Systematic Comparison of LLM Training Approaches](https://md.research.elamur.ai/free/en/papers/shirai-2026-generalization-graph-reasoning-systematic-comparison/)**Sola Shirai, Kavitha Srinivas, Julian Dolby et al.*our summary*
11. **[Map-of-Actions: Deliberate Reasoning over Multi-Labeled Graphs](https://md.research.elamur.ai/free/en/papers/ni-2026-map-actions-deliberate-reasoning-over/)**Wuguang Ni, Kai Yang*our summary*
12. **[Mixed-Policy GRPO for Text-to-SQL with Off-Policy Data Generation](https://md.research.elamur.ai/free/en/papers/sterbentz-2026-mixed-policy-grpo-text-sql/)**Marko Sterbentz, Michael Glass, Nhan H Pham et al.*our summary*
13. **[Modeling LLM Agent Reviewer Dynamics in Elo-Ranked Review System ↗](https://aclanthology.org/2026.surgellm-1.11/)**Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen et al.
14. **[Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model ↗](https://aclanthology.org/2026.surgellm-1.3/)**Daehui Kim, Deokhyung Kang, Sangwon Ryu et al.
15. **[Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space](https://md.research.elamur.ai/free/en/papers/materzok-2026-output-space-search-targeting-llm/)**Tobias Materzok*our summary*
16. **[RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners ↗](https://aclanthology.org/2026.surgellm-1.7/)**Jugal Gajjar, Kamalasankari Subramaniakuppusamy
17. **[Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness on Tax Law ↗](https://aclanthology.org/2026.surgellm-1.23/)**Parisa Kordjamshidi, Samer Aslan, Madhavan Seshadri et al.
18. **[Routing End User Queries to Enterprise Databases](https://md.research.elamur.ai/free/en/papers/sudarshan-2026-routing-end-user-queries-enterprise/)**Saikrishna Sudarshan, Tanay Kulkarni, Manasi Patwardhan et al.*our summary*
19. **[SchemaScope: How Join-Hop Depth Breaks Text-to-SQL in Large Language Models, and a Decomposition-Based Remedy ↗](https://aclanthology.org/2026.surgellm-1.17/)**Kaustubh S. Bukkapatnam, Rayan Malik
20. **[StructSurvey: Structured Agentic Retrieval for Automated Survey Paper Generation](https://md.research.elamur.ai/free/en/papers/pedinotti-2026-structsurvey-structured-agentic-retrieval-automated/)**Paolo Pedinotti, Enrico Santus*our summary*
21. **[TabBridge: Bridging Structure and Context for Accurate Table Reasoning ↗](https://aclanthology.org/2026.surgellm-1.14/)**Jeongwoo Lee, Eunsoo Lee, Jihie Kim
22. **[TabFaith: Benchmarking and Improving Structural Faithfulness in LLM Table Summarization ↗](https://aclanthology.org/2026.surgellm-1.21/)**Kaustubh S. Bukkapatnam, Sohum Mehta
23. **[TabGuard: Agentic LLM Orchestration for Adaptive Tabular Anomaly Detection via Dynamic Validator Selection and Generation](https://md.research.elamur.ai/free/en/papers/unnikrishnan-2026-tabguard-agentic-llm-orchestration-adaptive/)**Srihari Unnikrishnan, Minghua Ma*our summary*
24. **[UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification ↗](https://aclanthology.org/2026.surgellm-1.1/)**Poojah Ganesan, Rajat Aayush Jha, Dan Roth et al.

## Papers with our summary in our library (14)

The most cited first (OpenAlex citations plus our library's).

1. **[TreeDiff: AST-Guided Code Generation with Diffusion LLMs](https://md.research.elamur.ai/free/en/papers/zeng-2026-treediff-ast-guided-code-generation/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Yiming Zeng, Jinghan Cao, Zexin Li, et al.*2026 · 3 citations*
2. **[More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval](https://md.research.elamur.ai/free/en/papers/zuo-2026-more-than-efficiency-embedding-compression/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Chunsheng Zuo, Daniel Khashabi*2026 · 2 citations*
3. **[StructSurvey: Structured Agentic Retrieval for Automated Survey Paper Generation](https://md.research.elamur.ai/free/en/papers/pedinotti-2026-structsurvey-structured-agentic-retrieval-automated/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Paolo Pedinotti, Enrico Santus*2026 · 1 citation*
4. **[The Mighty ToRR: A Benchmark for Table Reasoning and Robustness in LLMs](https://md.research.elamur.ai/free/en/papers/tahan-2026-mighty-torr-benchmark-table-reasoning/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Shir Ashury-Tahan, Yifan Mai, Rajmohan C, et al.*2026 · 1 citation*
5. **[Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards](https://md.research.elamur.ai/free/en/papers/zhang-2026-chart-rl-generalized-chart-comprehension/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Xin Zhang, Xingyu Li, Rongguang Wang, et al.*2026 · 1 citation*
6. **[Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space](https://md.research.elamur.ai/free/en/papers/materzok-2026-output-space-search-targeting-llm/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Tobias Materzok*2026*
7. **[Map-of-Actions: Deliberate Reasoning over Multi-Labeled Graphs](https://md.research.elamur.ai/free/en/papers/ni-2026-map-actions-deliberate-reasoning-over/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Wuguang Ni, Kai Yang*2026*
8. **[Can LLMs Self-Correct Table Reasoning Errors?](https://md.research.elamur.ai/free/en/papers/shaikh-2026-can-llms-self-correct-table/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Farseen Shaikh*2026*
9. **[Generalization in Graph Reasoning: A Systematic Comparison of LLM Training Approaches](https://md.research.elamur.ai/free/en/papers/shirai-2026-generalization-graph-reasoning-systematic-comparison/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Sola Shirai, Kavitha Srinivas, Julian Dolby, et al.*2026*
10. **[Asking language models how to represent data for fine-tuning](https://md.research.elamur.ai/free/en/papers/singh-2026-asking-language-models-how-represent/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Usneek Singh, Ananya Singha, Abhijeet Awasthi, et al.*2026*
11. **[Mixed-Policy GRPO for Text-to-SQL with Off-Policy Data Generation](https://md.research.elamur.ai/free/en/papers/sterbentz-2026-mixed-policy-grpo-text-sql/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Marko Sterbentz, Michael Glass, Nhan H Pham, et al.*2026*
12. **[Routing End User Queries to Enterprise Databases](https://md.research.elamur.ai/free/en/papers/sudarshan-2026-routing-end-user-queries-enterprise/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Saikrishna Sudarshan, Tanay Kulkarni, Manasi Patwardhan, et al.*2026*
13. **[TabGuard: Agentic LLM Orchestration for Adaptive Tabular Anomaly Detection via Dynamic Validator Selection and Generation](https://md.research.elamur.ai/free/en/papers/unnikrishnan-2026-tabguard-agentic-llm-orchestration-adaptive/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Srihari Unnikrishnan, Minghua Ma*2026*
14. **[DSMentor: Curriculum-Guided Inference with Online Memory for Data-Science LLM Agents](https://md.research.elamur.ai/free/en/papers/wang-2026-dsmentor-curriculum-guided-inference-online/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**He Wang, Alexander Hanbo Li, Yiqun Hu, et al.*2026*

## Top topics

Topics of its works in our library, with the number of works on each.

[Language models & pretraining (6)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning (4)](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Code & programming languages (2)](https://md.research.elamur.ai/free/en/topics/code-and-programming/) · [Information retrieval & search (2)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Semantic parsing & meaning representation (1)](https://md.research.elamur.ai/free/en/topics/semantic-parsing/)

## Fields

[Computer Science (14)](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities (13)](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Decision Sciences (1)](https://md.research.elamur.ai/free/en/shelves/decision-sciences/)

## Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

[🧑‍🔬**Tao Ren**1 work here · 3 citations](https://md.research.elamur.ai/free/en/authors/tao-ren/) · [🧑‍🔬**Yiming Chen**1 work here · 3 citations](https://md.research.elamur.ai/free/en/authors/yiming-chen/) · [🧑‍🔬**Chunsheng Zuo**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/chunsheng-zuo/) · [🧑‍🔬**Daniel Khashabi**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/daniel-khashabi/) · [🧑‍🔬**Ariel Gera**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/ariel-gera/) · [🧑‍🔬**Asaf Yehudai**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/asaf-yehudai/) · [🧑‍🔬**Dan Roth**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/dan-roth/) · [🧑‍🔬**Elron Bandel**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/elron-bandel/) · [🧑‍🔬**Enrico Santus**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/enrico-santus/) · [🧑‍🔬**Leshem Choshen**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/leshem-choshen/) · [🧑‍🔬**Michal Shmueli-Scheuer**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/michal-shmueli-scheuer/) · [🧑‍🔬**Paolo Pedinotti**1 work here · 1 citation](https://md.research.elamur.ai/free/en/authors/paolo-pedinotti/)

## Top institutions

Institutions on the bylines of its works here, by the number of works.

[🏢**Microsoft** Redmond · United States 2 works here](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🎓**Florida State University** Tallahassee · United States 1 work here](https://md.research.elamur.ai/free/en/universities/florida-state-university/) · [🎓**University of California, Riverside** Riverside · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-california-riverside/) · [🎓**Northwestern University** Evanston · United States 1 work here](https://md.research.elamur.ai/free/en/universities/northwestern-university/) · [🎓**Tongji University** Shanghai · China 1 work here](https://md.research.elamur.ai/free/en/universities/tongji-university/) · [🏢**Bloomberg** New York · United States 1 work here](https://md.research.elamur.ai/free/en/companies/bloomberg/) · [🎓**Georgia Institute of Technology** Atlanta · United States 1 work here](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) · [🏢**Amazon** Seattle · United States 1 work here](https://md.research.elamur.ai/free/en/companies/amazon/) · [🎓**University of Connecticut** Storrs · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-connecticut/) · [🎓**Johns Hopkins University** Baltimore · United States 1 work here](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) · [🎓**National University of Singapore** Singapore · Singapore 1 work here](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) · [🎓**University of Pittsburgh** Pittsburgh · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-pittsburgh/)

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

- [↑ back to Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)