# Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

arXiv: https://arxiv.org/abs/2402.13211 · HTML: https://mlsanity.com/paper/2402.13211/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2](https://mlsanity.com/paper/2311.10702/) (2023)
- [USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation](https://mlsanity.com/paper/2005.00456/) (2020)
- [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://mlsanity.com/paper/2312.15166/) (2023)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [Building Emotional Support Chatbots in the Era of LLMs](https://mlsanity.com/paper/2308.11584/) (2023)
- [Prompted LLMs as Chatbot Modules for Long Open-domain Conversation](https://mlsanity.com/paper/2305.04533/) (2023)
- [Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning](https://mlsanity.com/paper/2210.04242/) (2022)
- [Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations](https://mlsanity.com/paper/2305.10172/) (2023)
- [Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents](https://mlsanity.com/paper/2310.09343/) (2023)
- [PAL: Persona-Augmented Emotional Support Conversation Generation](https://mlsanity.com/paper/2212.09235/) (2022)
- [Controllable Mixed-Initiative Dialogue Generation through Prompting](https://mlsanity.com/paper/2305.04147/) (2023)
- [Efficient computation of rankings from pairwise comparisons](https://mlsanity.com/paper/2207.00076/) (2022)
- [TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition](https://mlsanity.com/paper/2305.03296/) (2023)
- [Rethinking Large Language Models in Mental Health Applications](https://mlsanity.com/paper/2311.11267/) (2023)
- [ChatGPT as a Therapist Assistant: A Suitability Study](https://mlsanity.com/paper/2304.09873/) (2023)
- [Knowledge-enhanced Memory Model for Emotional Support Conversation](https://mlsanity.com/paper/2310.07700/) (2023)

## Built on by (most cited first, 30 of 55)

- [Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory](https://mlsanity.com/paper/2407.03103/) (2024)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent](https://mlsanity.com/paper/2412.08389/) (2024)
- [PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents](https://mlsanity.com/paper/2509.17459/) (2025)
- [Depression Diagnosis Dialogue Simulation: Self-improving Psychiatrist with Tertiary Memory](https://mlsanity.com/paper/2409.15084/) (2024)
- [Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues](https://mlsanity.com/paper/2412.14584/) (2024)
- [Consistent Client Simulation for Motivational Interviewing-based Counseling](https://mlsanity.com/paper/2502.02802/) (2025)
- [Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation](https://mlsanity.com/paper/2502.17899/) (2025)
- [CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration](https://mlsanity.com/paper/2502.02807/) (2025)
- [The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation](https://mlsanity.com/paper/2501.07849/) (2025)
- [EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics](https://mlsanity.com/paper/2408.08782/) (2024)
- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)
- [You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations](https://mlsanity.com/paper/2512.15601/) (2025)
- [Empathy Through Multimodality in Conversational Interfaces](https://mlsanity.com/paper/2405.04777/) (2024)
- [Convert Language Model into a Value-based Strategic Planner](https://mlsanity.com/paper/2505.06987/) (2025)
- [Emotional Supporters often Use Multiple Strategies in a Single Turn](https://mlsanity.com/paper/2505.15316/) (2025)
- [DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization](https://mlsanity.com/paper/2505.16995/) (2025)
- [Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards](https://mlsanity.com/paper/2508.12935/) (2025)
- [PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions](https://mlsanity.com/paper/2509.07370/) (2025)
- [Emotional Support with LLM-based Empathetic Dialogue Generation](https://mlsanity.com/paper/2507.12820/) (2025)
- [PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics](https://mlsanity.com/paper/2601.03578/) (2026)
- [Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents](https://mlsanity.com/paper/2602.01405/) (2026)
- [The Interaction Layer: An Exploration for Co-Designing User-LLM Interactions in Parental Wellbeing Support Systems](https://mlsanity.com/paper/2411.01228/) (2024)
- [EmoFSM: A Finite State Machine for Emotional Support Conversation](https://mlsanity.com/paper/2504.11837/) (2025)
- [Affective Flow Language Model for Emotional Support Conversation](https://mlsanity.com/paper/2602.08826/) (2026)
- [Overview of the PsyDefDetect Shared Task at BioNLP 2026: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations](https://mlsanity.com/paper/2605.24907/) (2026)
- [Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity](https://mlsanity.com/paper/2505.23923/) (2025)
- [When LLMs Team Up: The Emergence of Collaborative Affective Computing](https://mlsanity.com/paper/2506.01698/) (2025)
- [Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics](https://mlsanity.com/paper/2508.18600/) (2025)
- [Human Psychometric Questionnaires Mischaracterize LLM Behavior](https://mlsanity.com/paper/2509.10078/) (2025)

## Abstract (arXiv)

Emotional Support Conversation (ESC) is a task aimed at alleviating individuals' emotional distress through daily conversation. Given its inherent complexity and non-intuitive nature, ESConv dataset incorporates support strategies to facilitate the generation of appropriate responses. Recently, despite the remarkable conversational ability of large language models (LLMs), previous studies have suggested that they often struggle with providing useful emotional support. Hence, this work initially analyzes the results of LLMs on ESConv, revealing challenges in selecting the correct strategy and a notable preference for a specific strategy. Motivated by these, we explore the impact of the inherent preference in LLMs on providing emotional support, and consequently, we observe that exhibiting high preference for specific strategies hinders effective emotional support, aggravating its robustness in predicting the appropriate strategy. Moreover, we conduct a methodological study to offer insights into the necessary approaches for LLMs to serve as proficient emotional supporters. Our findings emphasize that (1) low preference for specific strategies hinders the progress of emotional support, (2) external assistance helps reduce preference bias, and (3) existing LLMs alone cannot become good emotional supporters. These insights suggest promising avenues for future research to enhance the emotional intelligence of LLMs.