Camera-Ready Instructions

All accepted papers, including archival papers, Findings papers, and shared-task system papers, will be included in the workshop proceedings. Submit the final version through the relevant GroundLM OpenReview venue. Please revise the paper in response to the final decision and complete every item below before uploading.

• Address the decision letter: revise the paper to address the action items and substantive reviewer feedback identified in the final decision.
• Use the ACL camera-ready format: prepare the final PDF with the official ACL style files, without altering margins, fonts, spacing, or page dimensions.
• De-anonymize: include all authors, affiliations, acknowledgments, and any relevant funding or conflict-of-interest disclosures.
• Check references carefully: every cited work must exist and its title and author list must be accurate. EMNLP applies its paper-integrity policy to camera-ready papers.
• Validate the final PDF: ensure that it opens correctly and that figures, tables, links, and references render as intended. Run ACL PubCheck before uploading when possible.

Final Submission Portals

Questions

Please ask all camera-ready questions in the GroundLM Discord Q&A. Do not send camera-ready questions by email.

Shared-task system papers must meet all regular-paper requirements above. They must also report official online-evaluator results under the same team name used for evaluation and in the OpenReview teamname field. Clearly describe the submitted system, external data or models, prompts, training or inference setup, and limitations or error analysis. Accepted shared-task system papers will be included in the workshop proceedings.

• Upload your paper BibTeX entry: submit a separate .bib file containing the camera-ready metadata entry for your own system paper. Use the citation-key format <first-author-lastname>-2026-<method-acronym>, then replace the title and author fields with your final values. The title does not need to include a team name.
• Use task-specific BibTeX entries: include the benchmark references below in your own .bib file; do not rely on an unresolved citation key from another project.
• Cite both benchmark papers: all shared-task system papers must cite LitTraceQA and GoldenViewVQA, even when participating in only one task.
• Cite the findings paper: cite the shared-task findings paper using the BibTeX entry below.
• Keep materials reproducible: provide the submitted test outputs, code or a reproducibility package, and a complete disclosure of external datasets, pretrained models, tools, APIs, and synthetic data.

Required Paper BibTeX Upload

Upload a separate .bib file with one entry for your own shared-task system paper.

@inproceedings{firstauthorlastname-2026-method,
      title = {Your Paper Title},
      author = {Author One and Author Two},
      booktitle = {Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)}
}

Suggested Paper Titles

Use a concise, descriptive title that identifies the method and task; do not include the team name in the title. A useful pattern is <Method Name>: <Contribution> for <Task Name>.

• EvidenceRoute: View-Aware Reasoning for GoldenViewVQA
• SciTrace: Retrieval and Verification for LitTraceQA
• Unified Evidence Grounding Across Visual Driving Scenes and Scientific Literature for systems submitted to both shared tasks.

Required Shared-Task Citations

Copy the following entries into your bibliography file and cite them in the paper.

@inproceedings{wang-etal-2026-groundlm,
      title = {Findings of the First GroundLM Shared Tasks: Evaluating Grounded Language Models Across Visual and Scientific Evidence},
      author = {Wang, Yimu and Liu, Xuye and Choi, Yee Man and Xue, Bo and others},
      booktitle = {Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)},
      year = {2026}
}

@misc{liu2026littraceqabenchmarkmultistagegrounding,
      title={LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering},
      author={Xuye Liu and Yimu Wang and Peng Shi and Bo Xue and Xiangrui Ke and Songcheng Cai and Kath Choi and Di Wu and Freda Shi and Krzysztof Czarnecki},
      year={2026},
      eprint={2608.07370},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2608.07370},
}

@misc{wang2026doesanswercomefrom,
      title={Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving},
      author={Yimu Wang and Yee Man Choi and Barry Zhang and Mozhgan Nasr Azadani and Sean Sedwards and Krzysztof Czarnecki},
      year={2026},
      eprint={2606.09644},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.09644},
}