Luca Soldaini

The olmOCR Project: Building Fully Open OCR using VLMs ACL 2026 DataDecide: How to Predict Best Pretraining Data with Small Experiments ICML 2025 DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students’ Hand-Drawn Math Images NAACL 2025 FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions NAACL 2025 Language models scale reliably with over-training and on downstream tasks ICLR 2025 Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models CVPR 2025 OLMoE: Open Mixture-of-Experts Language Models ICLR 2025 OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens ACL 2025 Organize the Web: Constructing Domains Enhances Pre-Training Data Curation ICML 2025 RouterRetriever: Routing over a Mixture of Expert Embedding Models AAAI 2025 SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature EMNLP 2025 AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters ACL 2024 DataComp-LM: In search of the next generation of training sets for language models NeurIPS 2024 Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research ACL 2024 KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions ACL 2024 MathFish: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula EMNLP 2024 OLMo: Accelerating the Science of Language Models ACL 2024 Paloma: A Benchmark for Evaluating Language Model Fit NeurIPS 2024 What's In My Big Data? ICLR 2024 When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets EACL 2024 A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents EMNLP 2023 Embedding Recycling for Language Models EACL 2023 Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval EMNLP 2023 PaperMage: A Unified Toolkit for Processing, Representing, and Manipulating Visually-Rich Scientific Documents EMNLP 2023 Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation AACL 2022 Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems EMNLP 2022 Knowledge Transfer from Answer Ranking to Answer Generation EMNLP 2022 Paragraph-based Transformer Pre-training for Multi-Sentence Inference NAACL 2022 Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection EMNLP 2022 Answer Generation for Retrieval-based Question Answering Systems ACL 2021 Modeling Context in Answer Sentence Selection Systems on a Latency Budget EACL 2021 Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention COLING 2020 The Cascade Transformer: an Application for Efficient Answer Sentence Selection ACL 2020 GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification SemEval 2018 Helping or Hurting? Predicting Changes in Users’ Risk of Self-Harm Through Online Community Interactions NAACL 2018 RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses NAACL 2018 SMHD: a Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions COLING 2018 Matching Citation Text and Cited Spans in Biomedical Literature: a Search-Oriented Approach NAACL 2015