# All Learning Has an Emotional Basis, So Does Task-Oriented Dialogue

arXiv: https://arxiv.org/abs/2507.01594 · HTML: https://mlsanity.com/paper/2507.01594/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 2 Jul 2025.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Selective Experience Replay for Lifelong Learning](https://mlsanity.com/paper/1802.10269/) (2018)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?](https://mlsanity.com/paper/2306.01386/) (2023)
- [Large Language Models as Zero-shot Dialogue State Tracker through Function Calling](https://mlsanity.com/paper/2402.10466/) (2024)
- [LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization](https://mlsanity.com/paper/2011.09378/) (2020)
- [Theory of Mind in Large Language Models: Assessment and Enhancement](https://mlsanity.com/paper/2505.00026/) (2025)
- [ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format](https://mlsanity.com/paper/2211.17148/) (2022)
- [Dynamic Dialogue Policy for Continual Reinforcement Learning](https://mlsanity.com/paper/2204.05928/) (2022)
- [EmoUS: Simulating User Emotions in Task-Oriented Dialogues](https://mlsanity.com/paper/2306.01579/) (2023)
- [Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance](https://mlsanity.com/paper/2109.04349/) (2021)
- [DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit](https://mlsanity.com/paper/2207.12551/) (2022)
- [Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding](https://mlsanity.com/paper/2408.02361/) (2024)
- [A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2401.13789/) (2024)

## Built on by (most cited first, 2 of 2)

- [Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios](https://mlsanity.com/paper/2601.15290/) (2025)
- [PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues](https://mlsanity.com/paper/2604.18354/) (2026)

## Abstract (arXiv)

Task-oriented dialogue (ToD) systems aim to help users accomplish goals through natural language interaction. Beyond task success, effective ToD systems must also maintain positive emotional interaction and accurately convey information in inherently noisy and ambiguous conversational environments. Recent advances in large language models (LLMs) have substantially improved conversational fluency and contextual understanding. However, although emotion has been incorporated into existing ToD systems, its integration is typically confined to limited roles, restricting its influence on overall dialogue behaviour and user experience. To address this, we propose a novel end-to-end framework that combines fully lexicalised representations with an LLM backbone for improved semantic accuracy and employs online reinforcement learning with short-term emotional and long-term task-success rewards for joint optimisation of emotional interaction and task success. We further develop a challenging and realistic simulation environment that enables systematic evaluation across diverse ToD set-ups. Experiments show that incorporating coarse affective signals improves task success and sentiment rating in aggregate. Furthermore, integrating emotional interaction throughout the dialogue system using our proposed framework results in more pronounced improvements in both task success and user emotional experience.