Error message

  • Deprecated function: TYPO3\PharStreamWrapper\Manager::initialize(): Implicitly marking parameter $resolver as nullable is deprecated, the explicit nullable type must be used instead in include_once() (line 19 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/file.phar.inc).
  • Deprecated function: TYPO3\PharStreamWrapper\Manager::initialize(): Implicitly marking parameter $collection as nullable is deprecated, the explicit nullable type must be used instead in include_once() (line 19 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/file.phar.inc).
  • Deprecated function: TYPO3\PharStreamWrapper\Manager::__construct(): Implicitly marking parameter $resolver as nullable is deprecated, the explicit nullable type must be used instead in include_once() (line 19 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/file.phar.inc).
  • Deprecated function: TYPO3\PharStreamWrapper\Manager::__construct(): Implicitly marking parameter $collection as nullable is deprecated, the explicit nullable type must be used instead in include_once() (line 19 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/file.phar.inc).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in include_once() (line 352 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/sites/default/settings.php).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in include_once() (line 353 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/sites/default/settings.php).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in include_once() (line 361 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/sites/default/settings.php).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in include_once() (line 368 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/sites/default/settings.php).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in drupal_settings_initialize() (line 826 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/bootstrap.inc).
  • Warning: ini_set(): Session ini settings cannot be changed after headers have already been sent in drupal_settings_initialize() (line 835 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/bootstrap.inc).
  • Warning: session_name(): Session name cannot be changed after headers have already been sent in drupal_settings_initialize() (line 838 of /is/htdocs/wp1066709_HN3MCMCRY7/www/swj/includes/bootstrap.inc).

On General and Biomedical Text-to-Graph Large Language Models

Submitted by Sergio Consoli on 05/21/2025 - 01:27

Tracking #: 3892-5106

Authors: 
Lorenzo Bertolini
Roel Hulsman1
Sergio Consoli
Antonio Puertas Gallardo
Mario Ceresa

Responsible editor: 
Guest Editors KG Gen from Text 2023

Submission type: 
Full Paper
Abstract: 
Knowledge graphs and ontologies represent symbolic and factual information that can offer structured and interpretable knowledge. Extracting and manipulating this type of information is a crucial step in complex processes. While Large Language Models (LLMs) are known to be useful for extracting and enriching knowledge graphs and ontologies, previous work has largely focused on comparing architecture-specific models (e.g. encoder-decoder only) across benchmarks from similar domains. In this work, we provide a large-scale comparison of the performance of certain LLM features (e.g. model architecture and size) and task learning methods (fine-tuning vs. in-context learning (iCL)) on text-to-graph benchmarks in two domains, namely the general and biomedical ones. Experiments suggest that, in the general domain, small fine-tuned encoder-decoder models and mid-sized decoder-only models used with iCL reach overall comparable performance with high entity and relation recognition and moderate yet encouraging graph completion. Our results also suggest that, regardless of other factors, biomedical knowledge graphs are notably harder to learn and are better modelled by small fine-tuned encoder-decoder architectures. Pertaining to iCL, we analyse hallucinating behaviour related to sub-optimal prompt design, suggesting an efficient alternative to prompt engineering and prompt tuning for tasks with structured model output.
Full PDF Version: 
PDF icon swj3892.pdf
Previous Version: 
On General and Biomedical Text-to-Graph Large Language Models
Tags: 
Reviewed
Long-term Stable Link to Resources: 
https://github.com/jrcf7/txt2graphLLMs

Decision/Status: 
Accept