Variable Extraction for Model Recovery in Scientific Literature
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910708263813120 |
|---|---|
| author | Liu, Chunwei Noriega-Atala, Enrique Pyarelal, Adarsh Morrison, Clayton T Cafarella, Mike |
| author_facet | Liu, Chunwei Noriega-Atala, Enrique Pyarelal, Adarsh Morrison, Clayton T Cafarella, Mike |
| contents | The global output of academic publications exceeds 5 million articles per year, making it difficult for humans to keep up with even a tiny fraction of scientific output. We need methods to navigate and interpret the artifacts -- texts, graphs, charts, code, models, and datasets -- that make up the literature. This paper evaluates various methods for extracting mathematical model variables from epidemiological studies, such as ``infection rate ($α$),'' ``recovery rate ($γ$),'' and ``mortality rate ($μ$).'' Variable extraction appears to be a basic task, but plays a pivotal role in recovering models from scientific literature. Once extracted, we can use these variables for automatic mathematical modeling, simulation, and replication of published results.
We introduce a benchmark dataset comprising manually-annotated variable descriptions and variable values extracted from scientific papers. Based on this dataset, we present several baseline methods for variable extraction based on Large Language Models (LLMs) and rule-based information extraction systems. Our analysis shows that LLM-based solutions perform the best. Despite the incremental benefits of combining rule-based extraction outputs with LLMs, the leap in performance attributed to the transfer-learning and instruction-tuning capabilities of LLMs themselves is far more significant. This investigation demonstrates the potential of LLMs to enhance automatic comprehension of scientific artifacts and for automatic model recovery and simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_14569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Variable Extraction for Model Recovery in Scientific Literature Liu, Chunwei Noriega-Atala, Enrique Pyarelal, Adarsh Morrison, Clayton T Cafarella, Mike Information Retrieval Machine Learning The global output of academic publications exceeds 5 million articles per year, making it difficult for humans to keep up with even a tiny fraction of scientific output. We need methods to navigate and interpret the artifacts -- texts, graphs, charts, code, models, and datasets -- that make up the literature. This paper evaluates various methods for extracting mathematical model variables from epidemiological studies, such as ``infection rate ($α$),'' ``recovery rate ($γ$),'' and ``mortality rate ($μ$).'' Variable extraction appears to be a basic task, but plays a pivotal role in recovering models from scientific literature. Once extracted, we can use these variables for automatic mathematical modeling, simulation, and replication of published results. We introduce a benchmark dataset comprising manually-annotated variable descriptions and variable values extracted from scientific papers. Based on this dataset, we present several baseline methods for variable extraction based on Large Language Models (LLMs) and rule-based information extraction systems. Our analysis shows that LLM-based solutions perform the best. Despite the incremental benefits of combining rule-based extraction outputs with LLMs, the leap in performance attributed to the transfer-learning and instruction-tuning capabilities of LLMs themselves is far more significant. This investigation demonstrates the potential of LLMs to enhance automatic comprehension of scientific artifacts and for automatic model recovery and simulation. |
| title | Variable Extraction for Model Recovery in Scientific Literature |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2411.14569 |