Table of Contents

• Overview of the Fifth Workshop on Scholarly Document ProcessingTirthankar Ghosal, Philipp Mayr 0001, Anita de Waard, Aakanksha Naik, Amanpreet Singh, Dayne Freitag, Georg Rehm, Sonja Schimmler, Dan Li. 1-6 [doi]
• TeXpert: A Multi-Level Benchmark for Evaluating LaTeX Code Generation by LLMsSahil Kale, Vijaykant Nadadur. 7-16 [doi]
• MathD2: Towards Disambiguation of Mathematical TermsShufan Jiang 0001, Mary Ann Tan, Harald Sack. 17-30 [doi]
• GraphTranslate: Predicting Clinical Trial Translation using Graph Neural Networks on Biomedical LiteratureEmily Muller, Justin Boylan-Toomey, Jack Ekinsmyth, Arne Robben, María De La Paz Cardona, Antonia Langfelder. 31-41 [doi]
• The ClimateCheck Dataset: Mapping Social Media Claims About Climate Change to Corresponding Scholarly ArticlesRaia Abu Ahmad, Aida Usmanova, Georg Rehm. 42-56 [doi]
• Analyzing the Evolution of Scientific Misconduct Based on the Language of Retracted PapersChristof Bless, Andreas Waldis, Angelina Parfenova, Maria A. Rodriguez 0002, Andreas Marfurt. 57-71 [doi]
• Collage: Decomposable Rapid Prototyping for Co-Designed Information Extraction on Scientific PDFsSireesh Gururaja, Yueheng Zhang, Guannan Tang, Tianhao Zhang, Kevin Murphy, Yu-Tsen Yi, Junwon Seo, Anthony D. Rollett, Emma Strubell. 72-82 [doi]
• Literature discovery with natural language queriesAnna Kiepura, Jessica Lam, Nianlong Gu, Richard H. R. Hahnloser. 83-95 [doi]
• Literature-Grounded Novelty Assessment of Scientific IdeasSimra Shahid, Marissa Radensky, Raymond Fok, Pao Siangliulue, Daniel S. Weld, Tom Hope. 96-113 [doi]
• Data Gatherer: LLM-Powered Dataset Reference Extraction from Scientific LiteraturePietro Marini, Aécio S. R. Santos, Nicole Contaxis, Juliana Freire. 114-123 [doi]
• Predicting The Scholarly Impact of Research Papers Using Retrieval-Augmented LLMsTamjid Azad, Ibrahim Al Azher, Sagnik Ray Choudhury, Hamed Alhoori. 124-131 [doi]
• Document Attribution: Examining Citation Relationships using Large Language ModelsVipula Rawte, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka. 132-136 [doi]
• SOMD2025: A Challenging Shared Tasks for Software Related Information ExtractionSharmila Upadhyaya, Wolfgang Otto 0002, Frank Krüger 0001, Stefan Dietze. 137-145 [doi]
• From In-Distribution to Out-of-Distribution: Joint Loss for Improving Generalization in Software Mention and Relation ExtractionStasa Mandic, Georg Niess, Roman Kern. 146-153 [doi]
• SOMD 2025: Fine-tuning ModernBERT for In- and Out-of-Distribution NER and Relation Extraction of Software Mentions in Scientific TextsVaghawan Ojha, Projan Shakya, Kristina Ghimire, Kashish Bataju, Ashwini Mandal, Sadikshya Gyawali, Manish Dahal, Manish Awale, Shital Adhikari, Sanjay Rijal. 154-163 [doi]
• Inductive Learning on Heterogeneous Graphs Enhanced by LLMs for Software Mention DetectionGabriel Silva, Mário Rodriges, António J. S. Teixeira, Marlene Amorim. 164-172 [doi]
• Extracting Software Mentions and Relations using Transformers and LLM-Generated Synthetic Data at SOMD 2025Pranshu Rastogi, Rajneesh Tiwari. 173-181 [doi]
• SciVQA 2025: Overview of the First Scientific Visual Question Answering Shared TaskEkaterina Borisova 0002, Nikolas Rauscher, Georg Rehm. 182-210 [doi]
• Visual Question Answering on Scientific Charts Using Fine-Tuned Vision-Language ModelsFlorian Schleid, Jan Strich, Chris Biemann. 211-220 [doi]
• ExpertNeurons at SciVQA-2025: Retrieval Augmented VQA with Vision Language Model (RAVQA-VLM)Nagaraj N. Bhat, Joydeb Mondal, Srijon Sarkar. 221-229 [doi]
• Coling-UniA at SciVQA 2025: Few-Shot Example Retrieval and Confidence-Informed Ensembling for Multimodal Large Language ModelsChristian Jaumann, Annemarie Friedrich, Rainer Lienhart. 230-239 [doi]
• Instruction-tuned QwenChart for Chart Question AnsweringViviana Ventura, Lukas Kleybolte, Alessandra Zarcone. 240-251 [doi]
• Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble ModelingPrahitha Movva, Naga Harshita Marupaka. 252-262 [doi]
• The ClimateCheck Shared Task: Scientific Fact-Checking of Social Media Claims about Climate ChangeRaia Abu Ahmad, Aida Usmanova, Georg Rehm. 263-275 [doi]
• Winning ClimateCheck: A Multi-Stage System with BM25, BGE-Reranker Ensembles, and LLM-based Analysis for Scientific Abstract RetrievalJunjun Wang, Kunlong Chen, Zhaoqun Chen, Peng He, Wenlu Zheng. 276-280 [doi]
• Comparing LLMs and BERT-based Classifiers for Resource-Sensitive Claim Verification in Social MediaMax Upravitelev, Nicolau Duran-Silva, Christian Woerle, Giuseppe Guarino, Salar Mohtaj, Jing Yang, Veronika Solopova, Vera Schmitt. 281-287 [doi]
• AlexUNLP-FMT at ClimateCheck Shared Task: Hybrid Retrieval with Adaptive Similarity Graph-based Reranking for Climate-related Social Media Claims Fact CheckingMahmoud Fathallah, Nagwa M. El-Makky, Marwan Torki. 288-292 [doi]
• ClimateCheck2025: Multi-Stage Retrieval Meets LLMs for Automated Scientfic Fact-CheckingAnna Kiepura, Jessica Lam. 293-306 [doi]
• Overview of the SciHal25 Shared Task on Hallucination Detection for Scientific ContentDan Li 0015, Bogdan Palfi, Colin Zhang, Jaiganesh Subramanian, Adrian Raudaschl, Yoshiko Kakita, Anita de Waard, Zubair Afzal, Georgios Tsatsaronis. 307-315 [doi]
• Detecting Hallucinations in Scientific Claims by Combining Prompting Strategies and Internal State ClassificationYupeng Cao, Chun-Nam Yu, K. P. Subbalakshmi. 316-327 [doi]
• A.M.P at SciHal2025: Automated Hallucination Detection in Scientific Content via LLMs and Prompt EngineeringLe Nguyen Anh Khoa, Thìn Dang Van. 328-335 [doi]
• SciBERT Meets Contrastive Learning: A Solution for Scientific Hallucination DetectionCrivoi Carla, Ana Sabina Uban. 336-343 [doi]
• Natural Language Inference Fine-tuning for Scientific Hallucination DetectionTim Schopf, Juraj Vladika, Michael Färber 0001, Florian Matthes. 344-352 [doi]
• From RAG to Reality: Coarse-Grained Hallucination Detection via NLI Fine-TuningDaria Galimzianova, Aleksandr Boriskin, Grigory Arshinov. 353-359 [doi]