Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment

• URL: http://arxiv.org/abs/2512.04210v1
• Date: Wed, 03 Dec 2025 19:30:07 GMT
• Title: Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
• Authors: Huy Nghiem, Swetasudha Panda, Devashish Khatwani, Huy V. Nguyen, Krishnaram Kenthapadi, Hal Daumé,
• Abstract summary: Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment.<n>We present an iterative post-deployment alignment framework that applies Kahneman-Tversky Optimization (KTO) and Direct Preference Optimization (DPO) to refine models against domain-specific safety signals.
• Score: 9.422745886489801
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants must avoid unsafe compliance without over-refusing benign queries. We present an iterative post-deployment alignment framework that applies Kahneman-Tversky Optimization (KTO) and Direct Preference Optimization (DPO) to refine models against domain-specific safety signals. Using the CARES-18K benchmark for adversarial robustness, we evaluate four LLMs (Llama-3B/8B, Meditron-8B, Mistral-7B) across multiple cycles. Our results show up to 42% improvement in safety-related metrics for harmful query detection, alongside interesting trade-offs against erroneous refusals, thereby exposing architecture-dependent calibration biases. We also perform ablation studies to identify when self-evaluation is reliable and when external or finetuned judges are necessary to maximize performance gains. Our findings underscore the importance of adopting best practices that balance patient safety, user trust, and clinical utility in the design of conversational medical assistants.

Related papers

• Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification [60.18369393468405]
  Existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration.<n>GLEAN compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals.<n>We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset.
  arXiv  Detail & Related papers  (2026-03-03T09:36:43Z)
• Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context [82.32380418146656]
  Health-ORSC-Bench is the first large-scale benchmark designed to measure textbfOver-Refusal and textbfSafe Completion quality in healthcare.<n>Our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity.<n>Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants.
  arXiv  Detail & Related papers  (2026-01-25T01:28:52Z)
• Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering [6.782185804809171]
  Large Language Models in Medical Question Answering severely hampered by ambiguous user queries.<n>In this paper, we formalize this challenge by linking input ambiguity to aleatoric uncertainty (AU), which is the irreducible uncertainty arising from underspecified input.<n>We introduce a novel AU-guided "Clarify-Before-Answer" framework, which incorporates AU-Probe - a lightweight module that detects input ambiguity directly from hidden states.
  arXiv  Detail & Related papers  (2026-01-24T03:44:08Z)
• Automated Rubrics for Reliable Evaluation of Medical Dialogue Systems [19.880569341968023]
  Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety.<n>We propose a retrieval-augmented multi-agent framework designed to automate the generation of instance-specific evaluation rubrics.
  arXiv  Detail & Related papers  (2026-01-21T16:40:41Z)
• Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops [1.412167203558403]
  Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment.<n>This work introduces a multi-agent refinement framework designed to enhance the safety and reliability of medical LLMs through structured, iterative alignment.
  arXiv  Detail & Related papers  (2026-01-19T18:10:34Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Rethinking Safety in LLM Fine-tuning: An Optimization Perspective [56.31306558218838]
  We show that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts.<n>We propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance.<n>Our experiments on the Llama families across multiple datasets demonstrate that safety problems can largely be avoided without specialized interventions.
  arXiv  Detail & Related papers  (2025-08-17T23:46:36Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models [4.035767214877404]
  We introduce Prompt4Trust, the first reinforcement learning framework for prompt augmentation targeting confidence calibration in MLLMs.<n>Unlike conventional calibration techniques, Prompt4Trust specifically prioritizes aspects of calibration most critical for safe and trustworthy clinical decision-making.<n>Our framework showed promising zero-shot generalizations to larger MLLMs in our experiments.
  arXiv  Detail & Related papers  (2025-07-12T13:21:10Z)
• Aurora: Are Android Malware Classifiers Reliable and Stable under Distribution Shift? [51.12297424766236]
  AURORA is a framework to evaluate malware classifiers based on their confidence quality and operational resilience.<n>AURORA is complemented by a set of metrics designed to go beyond point-in-time performance.<n>The fragility in SOTA frameworks across datasets of varying drift suggests the need for a return to the whiteboard.
  arXiv  Detail & Related papers  (2025-05-28T20:22:43Z)
• Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models [94.39278422567955]
  Fine-tuning large language models (LLMs) on human preferences has proven successful in enhancing their capabilities.<n>However, ensuring the safety of LLMs during fine-tuning remains a critical concern.<n>We propose a supervised learning framework called Bi-Factorial Preference Optimization (BFPO) to address this issue.
  arXiv  Detail & Related papers  (2024-08-27T17:31:21Z)

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.