# Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.01282 · HTML: https://mlsanity.com/paper/2512.01282/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [RewardBench 2: Advancing Reward Model Evaluation](https://mlsanity.com/paper/2506.01937/) (2025)
- [Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model](https://mlsanity.com/paper/2508.06206/) (2025)
- [Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning](https://mlsanity.com/paper/2508.10848/) (2025)
- [Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling](https://mlsanity.com/paper/2505.15715/) (2025)
- [Reinforcement Learning with Token-level Feedback for Controllable Text Generation](https://mlsanity.com/paper/2403.11558/) (2024)
- [ASEM: Enhancing Empathy in Chatbot through Attention-based Sentiment and Emotion Modeling](https://mlsanity.com/paper/2402.16194/) (2024)
- [SYNTHEMPATHY: A Scalable Empathy Corpus Generated Using LLMs Without Any Crowdsourcing](https://mlsanity.com/paper/2502.17857/) (2025)
- [EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization](https://mlsanity.com/paper/2406.19071/) (2024)

## Built on by (most cited first, 22 of 22)

- [Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling](https://mlsanity.com/paper/2601.21684/) (2026)
- [PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models](https://mlsanity.com/paper/2601.10532/) (2026)
- [TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization](https://mlsanity.com/paper/2601.22776/) (2026)
- [CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship](https://mlsanity.com/paper/2608.02046/) (2026)
- [EchoRL: Reinforcement Learning via Rollout Echoing](https://mlsanity.com/paper/2605.31228/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning](https://mlsanity.com/paper/2602.10622/) (2026)
- [MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue](https://mlsanity.com/paper/2603.06194/) (2026)
- [Compatibility-Aware Dynamic Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2606.11206/) (2026)
- [HeartBench: Probing Core Dimensions of Anthropomorphic Intelligence in LLMs](https://mlsanity.com/paper/2512.21849/) (2025)
- [Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models](https://mlsanity.com/paper/2601.22574/) (2026)
- [Query as Anchor: Scenario-Adaptive User Representation via Large Language Model](https://mlsanity.com/paper/2602.14492/) (2026)
- [ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship](https://mlsanity.com/paper/2604.18356/) (2026)
- [LifeSide: Benchmarking Agents as Lifelong Digital Companions](https://mlsanity.com/paper/2606.04660/) (2026)
- [Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning](https://mlsanity.com/paper/2602.03516/) (2026)
- [AE-LLM: Adaptive Efficiency Optimization for Large Language Models](https://mlsanity.com/paper/2603.20492/) (2026)
- [From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users](https://mlsanity.com/paper/2606.00728/) (2026)
- [MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models](https://mlsanity.com/paper/2606.11792/) (2026)
- [Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support](https://mlsanity.com/paper/2606.30887/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)
- [Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations](https://mlsanity.com/paper/2607.28648/) (2026)
- [Evolving Support Priorities in Empathetic Reinforcement Learning](https://mlsanity.com/paper/2609.34249/) (2026)

## Abstract (arXiv)

As web platforms evolve towards greater personalization and emotional complexity, conversational agents must transcend superficial empathy to demonstrate identity-aware emotional reasoning. However, existing systems face two limitations: (1) reliance on situation-centric datasets lacking persistent user identity, which hampers the capture of personalized affective nuances; and (2) dependence on opaque, coarse reward signals that hinder development of verifiable empathetic reasoning. To address these gaps, we introduce KardiaBench, a large-scale user-grounded benchmark comprising 178,080 QA pairs across 22,080 multi-turn conversations anchored to 671 real-world profiles. The dataset is constructed via a model-in-the-loop pipeline with iterative rubric-guided refinement to ensure psychological plausibility and persona consistency. This progressive empathy pipeline that integrates user comprehension, contextual reasoning, and emotion perception into conversations, followed by iterative critique and rubric-based refinement to ensure psychological plausibility, emotional fidelity, and persona consistency. Building on this, we propose Kardia-R1, a framework that trains models for interpretable, stepwise empathetic cognition. Kardia-R1 leverages Rubric-as-Judge Empathetic Reinforcement Learning (Rubric-ERL), a GRPO-based method that uses explainable, human-aligned rubric rewards to tightly couple user understanding, emotional inference, and supportive response generation. Extensive experiments across four LLM backbones demonstrate that Kardia-R1 consistently outperforms othet methods in emotion accuracy, empathy, relevance, persona consistency, and safety. Our dataset and model will be released at https://github.com/JhCircle/Kardia-R1.