mlsanityData to 14 Oct 2026

Aligning (Medical) LLMs for (Counterfactual) Fairness

arXiv 2408.12055 ↗First posted 22 Aug 2024cs.CL cs.LGcited by 7

On the map: LLM alignment / RLHF / preference optimisation → Medical LLM alignment

Abstract (arXiv)

Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of individuals, worsening health disparities, and reducing trust in AI-augmented medical tools. Aiming to address this important issue, in this study, we present a new model alignment approach for aligning LLMs using a preference optimization method within a knowledge distillation framework. Prior to presenting our proposed method, we first use an evaluation framework to conduct a comprehensive (largest to our knowledge) empirical evaluation to reveal the type and nature of existing biases in LLMs used for medical applications. We then offer a bias mitigation technique to reduce the unfair patterns in LLM outputs across different subgroups identified by the protected attributes. We show that our mitigation method is effective in significantly reducing observed biased patterns. Our code is publicly available at urlhttps://github.com/healthylaife/FairAlignmentLLM.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 30 of its 56 references that are in the map. First posted on arXiv 22 Aug 2024.

Builds on

30 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Aligning Large Language Models for Clinical Tasks6 Sep

Other references · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  8. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  9. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  10. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  11. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  12. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 912
17 more
  1. 2017Counterfactual Fairnesscited by 804
  2. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  3. 2023Towards Generalist Biomedical AIcited by 289
  4. 2023MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Datacited by 286
  5. 2023MEDITRON-70B: Scaling Medical Pretraining for Large Language Modelscited by 274
  6. 2023Fine-tuning Language Models for Factualitycited by 221
  7. 2024A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicitycited by 185
  8. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 153
  9. 2020Evolution of Semantic Similarity -- A Surveycited by 83
  10. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  11. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 47
  12. 2024A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Modelscited by 45
  13. 2024LoRA Dropout as a Sparsity Regularizer for Overfitting Controlcited by 35
  14. 2024Bias patterns in the application of LLMs for clinical decision support: A comprehensive studycited by 27
  15. 2023Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methodscited by 17
  16. 2021Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Managementcited by 16
  17. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 1.

7 papers.

  1. 2024Enabling Scalable Evaluation of Bias Patterns in Medical LLMscited by 5
  2. 2025ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphscited by 3
  3. 2025HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learningcited by 3
  4. 2024Lookahead Counterfactual Fairnesscited by 2
  5. 2025How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Datasetcited by 1
  6. 2026FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistantscited by 1
  7. 2025Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Promptingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment
  2. 2025ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making
  3. 2024Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions
  4. 2025SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization
  5. 2026First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
  6. 2025MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning
  7. 2025Toward Revealing Nuanced Biases in Medical LLMs
  8. 2026A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics