Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916822196944896 |
|---|---|
| author | Feng, Shutong Lin, Hsien-chin Lubis, Nurul van Niekerk, Carel Heck, Michael Ruppik, Benjamin Vukovic, Renato Gašić, Milica |
| author_facet | Feng, Shutong Lin, Hsien-chin Lubis, Nurul van Niekerk, Carel Heck, Michael Ruppik, Benjamin Vukovic, Renato Gašić, Milica |
| contents | Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) have significantly improved linguistic fluency and contextual understanding, building effective and emotionally intelligent ToD systems remains a complex challenge. Effective ToD systems must optimise for task success, emotional understanding and responsiveness, and precise information conveyance, all within inherently noisy and ambiguous conversational environments. In this work, we investigate architectural, representational, optimisational as well as emotional considerations of ToD systems. We set up systems covering these design considerations with a challenging evaluation environment composed of a natural-language user simulator coupled with an imperfect natural language understanding module. We propose \textbf{LUSTER}, an \textbf{L}LM-based \textbf{U}nified \textbf{S}ystem for \textbf{T}ask-oriented dialogue with \textbf{E}nd-to-end \textbf{R}einforcement learning with both short-term (user sentiment) and long-term (task success) rewards. Our findings demonstrate that combining LLM capability with structured reward modelling leads to more resilient and emotionally responsive ToD systems, offering a practical path forward for next-generation conversational agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation Feng, Shutong Lin, Hsien-chin Lubis, Nurul van Niekerk, Carel Heck, Michael Ruppik, Benjamin Vukovic, Renato Gašić, Milica Computation and Language Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) have significantly improved linguistic fluency and contextual understanding, building effective and emotionally intelligent ToD systems remains a complex challenge. Effective ToD systems must optimise for task success, emotional understanding and responsiveness, and precise information conveyance, all within inherently noisy and ambiguous conversational environments. In this work, we investigate architectural, representational, optimisational as well as emotional considerations of ToD systems. We set up systems covering these design considerations with a challenging evaluation environment composed of a natural-language user simulator coupled with an imperfect natural language understanding module. We propose \textbf{LUSTER}, an \textbf{L}LM-based \textbf{U}nified \textbf{S}ystem for \textbf{T}ask-oriented dialogue with \textbf{E}nd-to-end \textbf{R}einforcement learning with both short-term (user sentiment) and long-term (task success) rewards. Our findings demonstrate that combining LLM capability with structured reward modelling leads to more resilient and emotionally responsive ToD systems, offering a practical path forward for next-generation conversational agents. |
| title | Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.01594 |