# From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents

arXiv: https://arxiv.org/abs/2511.03143 · HTML: https://mlsanity.com/paper/2511.03143/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024)
- [HelpSteer2: Open-source dataset for training top-performing reward models](https://mlsanity.com/paper/2406.08673/) (2024)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [CEM: Commonsense-aware Empathetic Response Generation](https://mlsanity.com/paper/2109.05739/) (2021)
- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements](https://mlsanity.com/paper/2310.05140/) (2023)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [Chain of Empathy: Enhancing Empathetic Response of Large Language Models Based on Psychotherapy Models](https://mlsanity.com/paper/2311.04915/) (2023)
- [An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents](https://mlsanity.com/paper/2309.05076/) (2023)
- [Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2408.11599/) (2024)
- [Synth-Empathy: Towards High-Quality Synthetic Empathy Data](https://mlsanity.com/paper/2407.21669/) (2024)
- [SENSE-7: Taxonomy and Dataset for Measuring User Perceptions of Empathy in Sustained Human-AI Conversations](https://mlsanity.com/paper/2509.16437/) (2025)
- [EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization](https://mlsanity.com/paper/2406.19071/) (2024)
- [GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models](https://mlsanity.com/paper/2406.14903/) (2024)

## Built on by (most cited first, 1 of 1)

- [Discourse Diversity in Multi-Turn Empathic Dialogue](https://mlsanity.com/paper/2604.11742/) (2026)

## Abstract (arXiv)

Empathy is a critical factor in fostering positive user experiences in conversational AI. While models can display empathy, it is often generic rather than tailored to specific tasks and contexts. In this work, we introduce a novel framework for developing and evaluating context-specific empathetic large language models (LLMs). We first analyze a real-world conversational dataset consisting of 672 multi-turn conversations across 8 tasks, revealing significant differences in terms of expected and experienced empathy before and after the conversations, respectively. To help minimize this gap, we develop a synthetic multi-turn conversational generation pipeline and steer responses toward our defined empathy patterns based on the context that more closely matches users' expectations. We then train empathetic expert adapters for context-specific empathy that specialize in varying empathy levels based on the recognized task. Our empirical results demonstrate a significant gap reduction of 72.66% between perceived and desired empathy with scores increasing by an average factor of 2.43 as measured by our metrics and reward models. Additionally, our trained empathetic expert adapters demonstrate superior effectiveness in preserving empathy patterns throughout conversation turns, outperforming system prompts, which tend to dramatically diminish in impact as conversations lengthen.