# RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems

arXiv: https://arxiv.org/abs/2509.10746 · HTML: https://mlsanity.com/paper/2509.10746/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models](https://mlsanity.com/paper/2312.06281/) (2023)
- [Emotional Intelligence of Large Language Models](https://mlsanity.com/paper/2307.09042/) (2023)
- [Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes](https://mlsanity.com/paper/1904.09612/) (2019)
- [Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning](https://mlsanity.com/paper/2210.12217/) (2022)
- [QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA](https://mlsanity.com/paper/2506.08123/) (2025)
- [Chain of Empathy: Enhancing Empathetic Response of Large Language Models Based on Psychotherapy Models](https://mlsanity.com/paper/2311.04915/) (2023)
- [Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior](https://mlsanity.com/paper/2407.02099/) (2024)
- [Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts](https://mlsanity.com/paper/2210.16865/) (2022)
- [Generic Temporal Reasoning with Differential Analysis and Explanation](https://mlsanity.com/paper/2212.10467/) (2022)
- [An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents](https://mlsanity.com/paper/2309.05076/) (2023)
- [Assessing Empathy in Large Language Models with Real-World Physician-Patient Interactions](https://mlsanity.com/paper/2405.16402/) (2024)
- [Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training](https://mlsanity.com/paper/2506.00386/) (2025)
- [ThinkTuning: Instilling Cognitive Reflections without Distillation](https://mlsanity.com/paper/2508.07616/) (2025)
- [Modeling Challenging Patient Interactions: LLMs for Medical Communication Training](https://mlsanity.com/paper/2503.22250/) (2025)
- [CC-LEARN: Cohort-based Consistency Learning](https://mlsanity.com/paper/2506.15662/) (2025)
- [Unified Explanations in Machine Learning Models: A Perturbation Approach](https://mlsanity.com/paper/2405.20200/) (2024)
- [Model Interpretation and Explainability: Towards Creating Transparency in Prediction Models](https://mlsanity.com/paper/2405.20794/) (2024)

## Built on by (most cited first, 3 of 3)

- [PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models](https://mlsanity.com/paper/2601.10532/) (2026)
- [Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications](https://mlsanity.com/paper/2510.17764/) (2025)
- [From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users](https://mlsanity.com/paper/2606.00728/) (2026)

## Abstract (arXiv)

Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for clinical trust. We present RECAP (Reflect-Extract-Calibrate-Align-Produce), an inference-time framework grounded in cognitive appraisal theory that decomposes patient input into auditable, appraisal-theoretic stages without retraining. Across multiple benchmarks and models from 8B to 120B parameters, RECAP improves alignment with human judgments, with gains inversely proportional to model scale. Intermediate outputs further reveal that models systematically underweight relational factors such as social support. In blinded evaluations, oncology fellows rated RECAP responses significantly higher than baselines with 76-88% win rates, demonstrating that principled prompting can enhance medical AI's emotional intelligence while maintaining the transparency required for clinical deployment.