# Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation

arXiv: https://arxiv.org/abs/2505.21033 · HTML: https://mlsanity.com/paper/2505.21033/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 7 of 7)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Nemotron-4 340B Technical Report](https://mlsanity.com/paper/2406.11704/) (2024)
- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [An Unsupervised Dialogue Topic Segmentation Model Based on Utterance Rewriting](https://mlsanity.com/paper/2409.07672/) (2024)

## Built on by (most cited first, 4 of 4)

- [ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents](https://mlsanity.com/paper/2601.07582/) (2026)
- [DASH: Dialogue-Aware Similarity and Handshake Recognition for Topic Segmentation in Public-Channel Conversations](https://mlsanity.com/paper/2512.15042/) (2025)
- [CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation](https://mlsanity.com/paper/2605.30668/) (2026)
- [Zero-Shot Cue-Grounded Topic Segmentation of Spoken Documents](https://mlsanity.com/paper/2609.34425/) (2026)

## Abstract (arXiv)

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.