Challenge: Large Language Models (LLMs) show great potential for expressing empathy, but often deliver generic responses that fail to address users’ specific needs.
Approach: They propose a self-evolution framework to help LLMs improve their responses to better align with users’ implicit preferences concerning personality, emotional state, and specific context.
Outcome: The proposed model significantly improves the model's performance in emotional support, reducing unhelpful responses and minimizing discrepancies between user preferences and model outputs.

Similar Papers

I Don’t Need Solution. I Need Emotional Support : Empathetic LLMs based on Emotional Validation (2026.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs) struggle to generate emotional support response, despite observing and reflecting on the help-seeker’s situation . Empathy drives the formation of constructive interpersonal and supportive relationships, including counseling for mental health care .
Approach: They propose to use a two-stage training process to enhance empathetic response generation through empathy acquisition and emotional validation alignment.
Outcome: The proposed method significantly improves empathetic response generation, achieving superior performance in both automatic and human evaluations.
DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing ESC data entangles psychological strategies and response content, making it difficult to construct high-quality preference pairs.
Approach: They propose a Decoupled ESC framework that decomposes the ESC task into two sequential subtasks: strategy planning and empathic response generation.
Outcome: The proposed framework outperforms baselines, reducing preference bias and improving response quality.
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach: They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome: The proposed framework improves strategy selection preferences at each dialogue turn.
Aligning LLMs with Individual Preferences via Interaction (2025.coling-main)

Copied to clipboard

Challenge: Existing studies on LLMs alignment focus on generalizing their behavior to generalized values such as helpfulness, harmlessness, and honesty.
Approach: They train large language models to "interact to align" to implicitly infer user preferences . they use a multi-turn preference dataset to generate a personalized alignment .
Outcome: The proposed method enables dynamic, personalized alignment via interaction with a multi-turn preference dataset.
EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User’s Internal World (2026.acl-long)

Copied to clipboard

Challenge: EmoHarbor is an evaluation framework that rewards generic empathetic responses but fails to assess whether the support is genuinely personalized to users’ unique psychological profiles and contextual needs.
Approach: They propose an automated evaluation framework that adopts a User-as-a-Judge paradigm by simulating the user's inner world.
Outcome: The proposed framework decomposes users' internal processes into three specialized roles and defines 10 evaluation dimensions of personalized support quality.
SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) are used in psychological counseling to provide universal advice.
Approach: They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning .
Outcome: Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues .
From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations (2025.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that LLMs can infer persona traits and subtle shifts in emotionality and extraversion occur . scalable solutions with reduced costs and enhanced data privacy are needed .
Approach: They explore the role of personas in the creation of emotional support conversations by LLMs.
Outcome: The proposed model can infer persona traits and maintain key persona characteristics while revealing shifts in emotionality and extraversion.
The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth (2024.naacl-long)

Copied to clipboard

Challenge: Queer youth face increased mental health risks, such as depression, anxiety, and suicidal ideation.
Approach: They propose a scale that is inspired by psychological standards and expert input to evaluate LLM's interactions with queer-related content.
Outcome: The proposed scale outperforms human responses to queer-related content and outperformed LLMs in the qualitative and quantitative analysis.
Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity (2026.eacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown growing potential in offering emotional support, but their ability to deliver culturally sensitive support remains underexplored due to a lack of resources.
Approach: They propose a large language model dataset that includes 1,729 distress messages, 1,523 cultural signals and 1,041 support strategies with fine-grained emotional and cultural annotations.
Outcome: The proposed models outperform peer-reviewed models and lack cultural sensitivity.
A Dual-Phase Self-Evolution Framework for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing strategies to optimize LLMs through pretraining fail to enhance domain cognition.
Approach: They propose a dual-phase self-evolution framework that integrates user preference adaptation and domain-specific competence to optimize LLMs.
Outcome: The proposed framework outperforms Supervised Fine-Tuning, Preference Optimization, and Memory-Augmented baselines on general NLP benchmarks and long-term dialogue tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations