Challenge: EmpatheticDialogues dataset provides a benchmark for empathetic dialogue generation . human evaluators perceive dialogue models as more epathetic .
Approach: They propose a benchmark for empathetic dialogue generation from a dataset of 25k conversations grounded in emotional situations.
Outcome: The proposed benchmarks show that existing models are perceived to be more empathetic by human evaluators compared to models trained on large-scale Internet conversations.

Similar Papers

A Taxonomy of Empathetic Response Intents in Human Social Conversations (2020.coling-main)

Copied to clipboard

Challenge: Open-domain conversational agents or chatbots are becoming increasingly popular in the natural language processing community.
Approach: They aim to combine dialogue act/intent modelling and neural response generation to produce a large-scale taxonomy for empathetic response intents.
Outcome: The proposed method improves the response quality of chatbots and makes them more controllable and interpretable.
Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements (2023.findings-emnlp)

Copied to clipboard

Challenge: Empathetic dialogue is an essential part of building harmonious social relationships and contributes to the development of a helpful AI.
Approach: They propose three methods to improve the performance of large language models (LLMs) they propose semantically similar in-context learning, two-stage interactive generation and combination with the knowledge base.
Outcome: The proposed methods achieve state-of-the-art in automatic and human evaluations and the possibility of GPT-4 simulating human evaluators.
EMPATH: An Ensemble Method for Automatic Fine-Grained Turn-Level Dialogue Empathy Evaluation with a Novel Emotional Distance Metric (2026.findings-acl)

Copied to clipboard

Challenge: Empathy evaluation metrics are lacking in the competitions, and classical dialogue evaluation metrics require further investigation.
Approach: They propose a framework which combines fine-tuned models, large language models, classical dialogue evaluation metrics, and a novel metric.
Outcome: The proposed framework improves on the WASSA 2024 benchmark and shows a statistically significant 8% improvement on the EX dataset.
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for dialogue empathy focus on the emotion flow in one direction, from context to response.
Approach: They propose a dual-generative model to construct emotional consensus and use unpaired data to produce pseudo paired empathetic samples.
Outcome: The proposed model outperforms baseline models in producing coherent and empathetic responses.
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing empathetic dialogue models only consider the affective aspect of empathy, which limits the capability of emotional response generation.
Approach: They propose a model that aligns the user's cognition and affection at both the coarse-grained and fine-grounded levels and then automatically and manually evaluates the model.
Outcome: The proposed model outperforms state-of-the-art models and generates more empathetic and informative responses.
Multi-Party Empathetic Dialogue Generation: A New Task for Dialog Systems (2022.acl-long)

Copied to clipboard

Challenge: Existing work on empathetic dialogues focused on the two-party scenario, but multi-party dialogues are pervasive in reality.
Approach: They propose a multi-party empathetic dialogue generation task that uses a static-dynamic model to explore emotion and sensibility.
Outcome: The proposed task is based on a model with static sensibility and dynamic emotion . it achieves state-of-the-art performance in multi-party empathetic dialogue learning .
Does GPT-3 Generate Empathetic Dialogues? A Novel In-Context Example Selection Method and Automatic Evaluation Metric for Empathetic Dialogue Generation (2022.coling-1)

Copied to clipboard

Challenge: Empathy is a multi-dimensional concept consisting of cognitive and affective aspects.
Approach: They propose two new in-context example selection methods that utilize emotion and situational information.
Outcome: The proposed method is effective in measuring the degree of human empathy.
E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Empathy is a desirable human trait that improves the emotional perceptivity in emotion-bonding social activities.
Approach: They propose a framework that integrates emotion correlation learning, utilization, and supervising.
Outcome: The proposed framework improves empathetic perception and expression on a humanized dialogue dataset.
From Traits to Empathy: Personality-Aware Multimodal Empathetic Response Generation (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches focus on acquiring affective and cognitive knowledge from text, but neglect the unique personality traits of individuals and the inherently multimodal nature of human face-to-face conversation.
Approach: They propose a multimodal dialogue system that generates empathetic responses from a perspective that considers the personality traits of users.
Outcome: The proposed system generates empathetic responses from a multimodal perspective and analyzes multimodal data to understand the user’s emotional state and situation.
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation (2020.coling-main)

Copied to clipboard

Challenge: Existing work on empathetic dialogue generation fails to capture the nuances of human emotion and consider the potential of user feedback.
Approach: They propose a multi-resolution adversarial model - EmpDG - to generate more empathetic responses by exploiting both coarse-grained dialogue-level and fine-grounded token-level emotions.
Outcome: The proposed model outperforms the state-of-the-art models in both content quality and emotion perceptivity.

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