# Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations

arXiv: https://arxiv.org/abs/2509.12661 · HTML: https://mlsanity.com/paper/2509.12661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?](https://mlsanity.com/paper/2405.05904/) (2024)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://mlsanity.com/paper/2307.11019/) (2023)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation](https://mlsanity.com/paper/2203.13560/) (2022)
- [Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation](https://mlsanity.com/paper/2402.09267/) (2024)
- [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)
- [Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation](https://mlsanity.com/paper/2204.12749/) (2022)
- [Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation](https://mlsanity.com/paper/2402.13211/) (2024)
- [Controllable Mixed-Initiative Dialogue Generation through Prompting](https://mlsanity.com/paper/2305.04147/) (2023)
- [TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition](https://mlsanity.com/paper/2305.03296/) (2023)
- [Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter](https://mlsanity.com/paper/2503.05362/) (2025)
- [Knowledge-enhanced Memory Model for Emotional Support Conversation](https://mlsanity.com/paper/2310.07700/) (2023)

## Abstract (arXiv)

Emotional support conversation (ESC) aims to alleviate distress through empathetic dialogue, yet large language models (LLMs) face persistent challenges in delivering effective ESC due to low accuracy in strategy planning. Moreover, there is a considerable preference bias towards specific strategies. Prior methods using fine-tuned strategy planners have shown potential in reducing such bias, while the underlying causes of the preference bias in LLMs have not well been studied. To address these issues, we first reveal the fundamental causes of the bias by identifying the knowledge boundaries of LLMs in strategy planning. Then, we propose an approach to mitigate the bias by reinforcement learning with a dual reward function, which optimizes strategy planning via both accuracy and entropy-based confidence for each region according to the knowledge boundaries. Experiments on the ESCov and ExTES datasets with multiple LLM backbones show that our approach outperforms the baselines, confirming the effectiveness of our approach.