# Generating Empathetic Responses by Looking Ahead the User's Sentiment

arXiv: https://arxiv.org/abs/1906.08487 · HTML: https://mlsanity.com/paper/1906.08487/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## Built on by (most cited first, 27 of 27)

- [A Mixture-of-Expert Approach to RL-based Dialogue Management](https://mlsanity.com/paper/2206.00059/) (2022)
- [HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback](https://mlsanity.com/paper/2403.08309/) (2024)
- [Discovering Emotion and Reasoning its Flip in Multi-Party Conversations using Masked Memory Network and Transformer](https://mlsanity.com/paper/2103.12360/) (2021)
- [Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities](https://mlsanity.com/paper/2206.05017/) (2022)
- [Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication](https://mlsanity.com/paper/2106.11791/) (2021)
- [Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy](https://mlsanity.com/paper/2205.07233/) (2022)
- [Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning](https://mlsanity.com/paper/2208.02294/) (2022)
- [Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation](https://mlsanity.com/paper/2408.02976/) (2024)
- [Dialogue Systems for Emotional Support via Value Reinforcement](https://mlsanity.com/paper/2501.17182/) (2025)
- [Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Data](https://mlsanity.com/paper/2103.04353/) (2021)
- [Empathetic Dialog Generation with Fine-Grained Intents](https://mlsanity.com/paper/2105.06829/) (2021)
- [A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots](https://mlsanity.com/paper/2401.00609/) (2023)
- [Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian](https://mlsanity.com/paper/2507.11299/) (2025)
- [Emotion Flip Reasoning in Multiparty Conversations](https://mlsanity.com/paper/2306.13959/) (2023)
- [E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation](https://mlsanity.com/paper/2311.15016/) (2023)
- [Towards Detecting Need for Empathetic Response in Motivational Interviewing](https://mlsanity.com/paper/2105.09649/) (2021)
- [Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation](https://mlsanity.com/paper/2109.07779/) (2021)
- [Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management](https://mlsanity.com/paper/2302.10850/) (2023)
- [PAGE: A Position-Aware Graph-Based Model for Emotion Cause Entailment in Conversation](https://mlsanity.com/paper/2303.01795/) (2023)
- [When to generate hedges in peer-tutoring interactions](https://mlsanity.com/paper/2307.15582/) (2023)
- [Open-Domain Dialogue Quality Evaluation: Deriving Nugget-level Scores from Turn-level Scores](https://mlsanity.com/paper/2310.00410/) (2023)
- [Cognitively Inspired Components for Social Conversational Agents](https://mlsanity.com/paper/2311.05450/) (2023)
- [Incongruent Positivity: When Miscalibrated Positivity Undermines Online Supportive Conversations](https://mlsanity.com/paper/2509.10184/) (2025)
- [Empathetic Response Generation with State Management](https://mlsanity.com/paper/2205.03676/) (2022)
- [Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems](https://mlsanity.com/paper/2412.04492/) (2024)
- [Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation](https://mlsanity.com/paper/2601.01037/) (2026)
- [Do You Understand How I Feel?: Towards Verified Empathy in Therapy Chatbots](https://mlsanity.com/paper/2601.08477/) (2026)

## Abstract (arXiv)

An important aspect of human conversation difficult for machines is conversing with empathy, which is to understand the user's emotion and respond appropriately. Recent neural conversation models that attempted to generate empathetic responses either focused on conditioning the output to a given emotion, or incorporating the current user emotional state. However, these approaches do not factor in how the user would feel towards the generated response. Hence, in this paper, we propose Sentiment Look-ahead, which is a novel perspective for empathy that models the future user emotional state. In short, Sentiment Look-ahead is a reward function under a reinforcement learning framework that provides a higher reward to the generative model when the generated utterance improves the user's sentiment. We implement and evaluate three different possible implementations of sentiment look-ahead and empirically show that our proposed approach can generate significantly more empathetic, relevant, and fluent responses than other competitive baselines such as multitask learning.