# PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text

arXiv: https://arxiv.org/abs/2605.28363 · HTML: https://mlsanity.com/paper/2605.28363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 9 of 9)

- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [BioRED: A Rich Biomedical Relation Extraction Dataset](https://mlsanity.com/paper/2204.04263/) (2022)
- [Benchmarking large language models for biomedical natural language processing applications and recommendations](https://mlsanity.com/paper/2305.16326/) (2023)
- [Financial Document Causality Detection Shared Task (FinCausal 2020)](https://mlsanity.com/paper/2012.02505/) (2020)
- [The Causal News Corpus: Annotating Causal Relations in Event Sentences from News](https://mlsanity.com/paper/2204.11714/) (2022)
- [Standardizing Structural Causal Models](https://mlsanity.com/paper/2406.11601/) (2024)
- [MIMICause: Representation and automatic extraction of causal relation types from clinical notes](https://mlsanity.com/paper/2110.07090/) (2021)
- [Domain Adaptative Causality Encoder](https://mlsanity.com/paper/2011.13549/) (2020)
- [Benchmarking LLMs for Pairwise Causal Discovery in Biomedical and Multi-Domain Contexts](https://mlsanity.com/paper/2601.15479/) (2026)

## Abstract (arXiv)

Causal relation extraction (CRE) is central to biomedical text mining, but current resources often conflate causal relations with broader associations, restrict annotation to sentence-level examples, or focus mainly on explicit causal cues. This limits their usefulness for evaluating whether models can recover causal claims as they are actually expressed in biomedical text. We introduce PubMedCausal, a span-level annotated corpus for biomedical CRE built from PubMed abstracts. The corpus contains 30,000 paragraph-level rows, including 3,945 causal rows and 6,491 adjudicated cause--effect pairs. Each causal relation is annotated with full-text cause and effect spans, causality type, and sententiality, enabling evaluation of both causal detection and full-span causal extraction. We benchmark discriminative encoders and open-source generative models across detection and extraction settings. For causal detection, biomedical encoders are strongest, with PubMedBERT reaching an F1 score of 0.7391. For span-level extraction, the best generative baseline is DeepSeek-R1-32B with few-shot prompting, reaching a Cosine Pair F1 of 0.6765. We further test transfer learning by evaluating PubMedCausal-trained encoders on external causal relation datasets, showing that the resource supports cross-dataset evaluation. Our results show that biomedical CRE remains difficult under class imbalance, long causal spans, implicit causality, inter-sentential relations, and prompt sensitivity. Code and Data can be found here: https://github.com/josiahpaul07/PubMedCausalExp