QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization
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_ | 1866915525365334016 |
|---|---|
| author | Ghebriout, Mohamed Imed Eddine Guibon, Gaël Lerner, Ivan Vincent, Emmanuel |
| author_facet | Ghebriout, Mohamed Imed Eddine Guibon, Gaël Lerner, Ivan Vincent, Emmanuel |
| contents | Dialogue summarization aims to distill the core meaning of a conversation into a concise text. This is crucial for reducing the complexity and noise inherent in dialogue-heavy applications. While recent approaches typically train language models to mimic human-written summaries, such supervision is costly and often results in outputs that lack task-specific focus limiting their effectiveness in downstream applications, such as medical tasks. In this paper, we propose \app, a framework for task-oriented utility-based dialogue summarization. \app starts by generating multiple summaries and task-oriented question-answer pairs from a dialogue in a zero-shot manner using a pool of large language models (LLMs). The quality of the generated summaries is evaluated by having LLMs answer task-related questions before \textit{(i)} selecting the best candidate answers and \textit{(ii)} identifying the most informative summary based on these answers. Finally, we fine-tune the best LLM on the selected summaries. When validated on multiple datasets, \app demonstrates its effectiveness by achieving competitive results in various zero-shot settings, rivaling fully-supervised State-of-the-Art (SotA) methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26302 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization Ghebriout, Mohamed Imed Eddine Guibon, Gaël Lerner, Ivan Vincent, Emmanuel Computation and Language Artificial Intelligence Dialogue summarization aims to distill the core meaning of a conversation into a concise text. This is crucial for reducing the complexity and noise inherent in dialogue-heavy applications. While recent approaches typically train language models to mimic human-written summaries, such supervision is costly and often results in outputs that lack task-specific focus limiting their effectiveness in downstream applications, such as medical tasks. In this paper, we propose \app, a framework for task-oriented utility-based dialogue summarization. \app starts by generating multiple summaries and task-oriented question-answer pairs from a dialogue in a zero-shot manner using a pool of large language models (LLMs). The quality of the generated summaries is evaluated by having LLMs answer task-related questions before \textit{(i)} selecting the best candidate answers and \textit{(ii)} identifying the most informative summary based on these answers. Finally, we fine-tune the best LLM on the selected summaries. When validated on multiple datasets, \app demonstrates its effectiveness by achieving competitive results in various zero-shot settings, rivaling fully-supervised State-of-the-Art (SotA) methods. |
| title | QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.26302 |