Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts

• URL: http://arxiv.org/abs/2501.06365v2
• Date: Wed, 28 May 2025 15:06:30 GMT
• Title: Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts
• Abstract summary: This paper presents a pipeline for mitigating gender bias in large language models used in medical literature by neutralizing gendered occupational pronouns.<n>A dataset of 379,000 PubMed abstracts from 1965 was processed to identify and modify pronouns tied to professions.
• Score: 3.7906296809297406
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper presents a pipeline for mitigating gender bias in large language models (LLMs) used in medical literature by neutralizing gendered occupational pronouns. A dataset of 379,000 PubMed abstracts from 1965-1980 was processed to identify and modify pronouns tied to professions. We developed a BERT-based model, "Modern Occupational Bias Elimination with Refined Training," or "MOBERT," trained on these neutralized abstracts, and compared its performance with "1965BERT," trained on the original dataset. MOBERT achieved a 70% inclusive replacement rate, while 1965BERT reached only 4%. A further analysis of MOBERT revealed that pronoun replacement accuracy correlated with the frequency of occupational terms in the training data. We propose expanding the dataset and refining the pipeline to improve performance and ensure more equitable language modeling in medical applications.

Related papers

• Model Retirement Creates Reproducibility Risk in Biomedical AI Publications [0.0]
  We searched PubMed for original research articles that applied a specific large language model to a biomedical task.<n>We identified 8,931 paper-model mentions spanning 5,242 unique publications.<n>Overall, 42% involved a model that was already retired by the time of official publication or is scheduled to retire within two years of publication.
  arXiv  Detail & Related papers  (2026-09-04T04:00:54Z)
• MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model [0.0]
  MedicalBERT is a pretrained BERT model trained on a large biomedicaldataset.<n>It is equipped with domain-specific vocabulary that enhances thecomprehension of biomedical terminology.<n>MedicalBERT surpasses the general-purpose BERT model by5.67% on average across all the tasks evaluated.
  arXiv  Detail & Related papers  (2025-07-06T03:38:05Z)
• DataComp-LM: In search of the next generation of training sets for language models [200.5293181577585]
  DataComp for Language Models (DCLM) is a testbed for controlled dataset experiments with the goal of improving language models. We provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations. Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing at model scales ranging from 412M to 7B parameters.
  arXiv  Detail & Related papers  (2024-06-17T17:42:57Z)
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• Medical Vision-Language Pre-Training for Brain Abnormalities [96.1408455065347]
  We show how to automatically collect medical image-text aligned data for pretraining from public resources such as PubMed. In particular, we present a pipeline that streamlines the pre-training process by initially collecting a large brain image-text dataset. We also investigate the unique challenge of mapping subfigures to subcaptions in the medical domain.
  arXiv  Detail & Related papers  (2024-04-27T05:03:42Z)
• UnMASKed: Quantifying Gender Biases in Masked Language Models through Linguistically Informed Job Market Prompts [0.0]
  This research delves into the inherent biases present in masked language models (MLMs) This study evaluated six prominent models: BERT, RoBERTa, DistilBERT, BERT-multilingual, XLM-RoBERTa, and DistilBERT-multilingual. The analysis reveals stereotypical gender alignment of all models, with multilingual variants showing comparatively reduced biases.
  arXiv  Detail & Related papers  (2024-01-28T23:00:40Z)
• Detecting Sexual Content at the Sentence Level in First Millennium Latin Texts [0.0]
  We introduce a novel corpus comprising around 2500 sentences spanning from 300 BCE to 900 CE including sexual semantics. We evaluate various sentence classification approaches and different input embedding layers, and show that all consistently outperform simple token-based searches.
  arXiv  Detail & Related papers  (2023-09-25T09:21:25Z)
• The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated [70.23064111640132]
  We compare the impact of debiasing on performance across multiple downstream tasks using a wide-range of benchmark datasets. Experiments show that the effects of debiasing are consistently emphunderestimated across all tasks.
  arXiv  Detail & Related papers  (2023-09-16T20:25:34Z)
• The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages [51.2321117760104]
  This paper describes the Gender-GAP Pipeline, an automatic pipeline to characterize gender representation in large-scale datasets for 55 languages. The pipeline uses a multilingual lexicon of gendered person-nouns to quantify the gender representation in text. We showcase it to report gender representation in WMT training data and development data for the News task, confirming that current data is skewed towards masculine representation.
  arXiv  Detail & Related papers  (2023-08-31T17:20:50Z)
• MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records [60.35217378132709]
  Large language models (LLMs) can follow natural language instructions with human-level fluency. evaluating LLMs on realistic text generation tasks for healthcare remains challenging. We introduce MedAlign, a benchmark dataset of 983 natural language instructions for EHR data.
  arXiv  Detail & Related papers  (2023-08-27T12:24:39Z)
• Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models [59.89454513692417]
  Tabular data is often hidden in text, particularly in medical diagnostic reports. We propose a novel, simple, and effective methodology for extracting structured tabular data from textual medical reports, called TEMED-LLM. We demonstrate that our approach significantly outperforms state-of-the-art text classification models in medical diagnostics.
  arXiv  Detail & Related papers  (2023-06-08T09:12:28Z)
• Textual Data Augmentation for Patient Outcomes Prediction [67.72545656557858]
  We propose a novel data augmentation method to generate artificial clinical notes in patients' Electronic Health Records. We fine-tune the generative language model GPT-2 to synthesize labeled text with the original training data. We evaluate our method on the most common patient outcome, i.e., the 30-day readmission rate.
  arXiv  Detail & Related papers  (2022-11-13T01:07:23Z)
• Learning structures of the French clinical language:development and validation of word embedding models using 21 million clinical reports from electronic health records [2.5709272341038027]
  Methods based on transfer learning using pre-trained language models have achieved state-of-the-art results in most NLP applications. We aimed to evaluate the impact of adapting a language model to French clinical reports on downstream medical NLP tasks.
  arXiv  Detail & Related papers  (2022-07-26T14:46:34Z)
• GERNERMED++: Transfer Learning in German Medical NLP [0.46408356903366527]
  We present a statistical model for German medical natural language processing trained for named entity recognition (NER) The work serves as a refined successor to our first GERNERMED model which is substantially outperformed by our work.
  arXiv  Detail & Related papers  (2022-06-29T09:53:10Z)
• "I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset [12.000335510088648]
  We present a new, more inclusive bias measurement dataset, HolisticBias, which includes nearly 600 descriptor terms across 13 different demographic axes. HolisticBias was assembled in a participatory process including experts and community members with lived experience of these terms. We demonstrate that HolisticBias is effective at measuring previously undetectable biases in token likelihoods from language models.
  arXiv  Detail & Related papers  (2022-05-18T20:37:25Z)
• Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting [88.83117372793737]
  Forgetting information in the original training data may damage the model's downstream performance by a large margin. We propose GEnder Equality Prompt (GEEP) to improve gender fairness of pre-trained models with less forgetting.
  arXiv  Detail & Related papers  (2021-10-11T15:52:16Z)
• Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance [0.11545092788508224]
  We identify and remove gendered language from two clinical-note datasets. We show minimal degradation in health condition classification tasks for low- to medium-levels of bias removal via data augmentation. This work outlines an interpretable approach for using data augmentation to identify and reduce the potential for bias in natural language processing pipelines.
  arXiv  Detail & Related papers  (2021-03-10T03:09:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.