DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation

• URL: http://arxiv.org/abs/2606.07894v1
• Date: Fri, 05 Jun 2026 23:08:02 GMT
• Title: DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation
• Abstract summary: Multi-party chat often contains interleaved dialogues because multiple participants can discuss different topics at the same time.<n> Dialogue disentanglement addresses this problem by separating an entangled utterance sequence into coherent dialogues.<n>This paper proposes an automatic prompt optimization for LLM based dialogue disentanglement.
• Score: 0.3580891736370874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-party chat often contains interleaved dialogues because multiple participants can discuss different topics at the same time. Dialogue disentanglement addresses this problem by separating an entangled utterance sequence into coherent dialogues. While large language models (LLMs) are promising for this task, they still struggle with dialogue disentanglement and achieve low accuracy. This paper proposes an automatic prompt optimization for LLM based dialogue disentanglement. We decompose the prompt into three components: task instruction, utterance representation, and output instruction, and optimize them using GEPA, an optimization method for compound AI systems. Experiments on benchmark datasets show that the optimized prompts improve dialogue disentanglement accuracy over the original prompts and can surpass hand crafted prompts.

Related papers

• ChatChecker: A Framework for Dialogue System Testing and Evaluation Through Non-cooperative User Simulation [0.0]
  ChatChecker is a framework for automated evaluation and testing of complex dialogue systems.<n>It uses large language models (LLMs) to simulate diverse user interactions, identify dialogue breakdowns, and evaluate quality.
  arXiv  Detail & Related papers  (2025-07-22T17:40:34Z)
• ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents [52.7201882529976]
  We propose SOP-guided Monte Carlo Tree Search (MCTS) planning framework to enhance controllability of dialogue agents.<n>To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o.<n>We also propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction.
  arXiv  Detail & Related papers  (2024-07-04T12:23:02Z)
• Unsupervised Extraction of Dialogue Policies from Conversations [3.102576158218633]
  We show how Large Language Models can be instrumental in extracting dialogue policies from datasets. We then propose a novel method for generating dialogue policies utilizing a controllable and interpretable graph-based methodology.
  arXiv  Detail & Related papers  (2024-06-21T14:57:25Z)
• OmniDialog: An Omnipotent Pre-training Model for Task-Oriented Dialogue System [43.92593448255296]
  We propose an Omnipotent Dialogue pre-training model ( OmniDialog) It unifies three dialogue tasks into a monolithic framework by multi-task learning, fostering inter-task communication. We evaluate its performance across four tasks: dialogue summarization, end-to-end dialogue modeling, dialogue state tracking, and intent classification.
  arXiv  Detail & Related papers  (2023-12-28T07:20:49Z)
• Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users [51.34484827552774]
  We release the Multi-User MultiWOZ dataset: task-oriented dialogues among two users and one agent. These dialogues reflect interesting dynamics of collaborative decision-making in task-oriented scenarios. We propose a novel task of multi-user contextual query rewriting: to rewrite a task-oriented chat between two users as a concise task-oriented query.
  arXiv  Detail & Related papers  (2023-10-31T14:12:07Z)
• Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models [52.24756457516834]
  We propose a novel "Self-Explanation" prompting strategy to enhance the comprehension abilities of Large Language Models (LLMs) This task-agnostic approach requires the model to analyze each dialogue utterance before task execution, thereby improving performance across various dialogue-centric tasks. Experimental results from six benchmark datasets confirm that our method consistently outperforms other zero-shot prompts and matches or exceeds the efficacy of few-shot prompts.
  arXiv  Detail & Related papers  (2023-09-22T15:41:34Z)
• Attribute Controlled Dialogue Prompting [31.09791656949115]
  We present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.
  arXiv  Detail & Related papers  (2023-07-11T12:48:55Z)
• Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems [22.302137281411646]
  Dial-MAE is a straightforward yet effective post-training technique tailored for dense encoders in dialogue response selection. Our experiments have demonstrated that Dial-MAE is highly effective, achieving state-of-the-art performance on two commonly evaluated benchmarks.
  arXiv  Detail & Related papers  (2023-06-07T11:40:07Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)
• Re$^3$Dial: Retrieve, Reorganize and Rescale Dialogue Corpus for Long-Turn Open-Domain Dialogue Pre-training [90.3412708846419]
  Most dialogues in existing pre-training corpora contain fewer than three turns of dialogue. We propose the Retrieve, Reorganize and Rescale framework (Re$3$Dial) to automatically construct billion-scale long-turn dialogues. By repeating the above process, Re$3$Dial can yield a coherent long-turn dialogue.
  arXiv  Detail & Related papers  (2023-05-04T07:28:23Z)
• Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems [8.419582942080927]
  Response generation is one of the critical components in task-oriented dialog systems. We propose an approach that performs textit dynamic prompting where the prompts are learnt from dialog contexts. We show that contextual dynamic prompts improve response generation in terms of textit combined score citemehri-etal 2019-structured by 3 absolute points.
  arXiv  Detail & Related papers  (2023-01-30T20:26:02Z)
• Manual-Guided Dialogue for Flexible Conversational Agents [84.46598430403886]
  How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be critical issues in building a task-oriented dialogue system. We propose a novel manual-guided dialogue scheme, where the agent learns the tasks from both dialogue and manuals. Our proposed scheme reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to adapt to various domains.
  arXiv  Detail & Related papers  (2022-08-16T08:21:12Z)
• TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue [113.45485470103762]
  In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
  arXiv  Detail & Related papers  (2020-04-15T04:09:05Z)
• Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems [57.082447660944965]
  Conversation Learner is a machine teaching tool for building dialog managers. It enables dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model. It allows dialog authors to improve the dialog manager over time by leveraging user-system dialog logs as training data.
  arXiv  Detail & Related papers  (2020-04-09T00:10:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.