ACL Findings2025
Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation
Seungmin Lee, Yongsang Yoo, Minhwa Jung, Min Song
Abstract
Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of recently proposed solutions. On the other hand, despite advances in Large Language Models (LLMs) and reasoning strategies, these have rarely been applied to DTS. This paper introduces Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation, which utilizes LLM-based multi-step deductive reasoning to enhance DTS performance and enable case study using intermediate result.
Our method employs a structured prompting approach for bidirectional context summarization, utterance intent classification, and deductive topic shift detection. In the intent classification process, we propose the generalizable intent list for domain-agnostic dialogue intent classification. Experiments in various dialogue settings demonstrate that Def-DTS consistently outperforms traditional and state-of-the-art approaches, with each subtask contributing to improved performance, particularly in reducing type 2 error. We also explore the potential for autolabeling, emphasizing the importance of LLM reasoning techniques in DTS. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on18
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
- GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-supervised Learning and Explicit Policy InjectionWanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu et al.AAAI 2022 · 181 citations
- DialogLM: Pre-trained Model for Long Dialogue Understanding and SummarizationMing Zhong, Yang Liu, Yichong Xu, Chenguang Zhu et al.AAAI 2022 · 150 citations
Related papers
- S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMsSarkar Snigdha Sarathi Das, Chirag Shah, Mengting Wan, Jennifer Neville et al.ACL Findings 2024 · 3 citations
- Do LLMs Understand Dialogues? A Case Study on Dialogue ActsAyesha Qamar, Jonathan Tong, Ruihong HuangACL 2025 · 8 citations
- DEBATE, TRAIN, EVOLVE: Self-Evolution of Language Model ReasoningGaurav Srivastava, Zhenyu Bi, Meng Lu, Xuan WangEMNLP 2025 · 1 citation
- Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural PlanningJiabao Kang, Xinye Li, Liyan Xu, Qingbin Liu et al.EMNLP Findings 2025
- Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought ReasoningWen Chang, Yun-Nung ChenACL Findings 2024 · 6 citations
