paper-with-me

홈 › Papers

DFlow: Diverse Dialogue Flow Simulation with Large Language Models

2024-10-18 · Wanyu Du, Song Feng, James Gung, Lijia Sun, Yi Zhang, Saab Mansour, Yanjun Qi

Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data augmentation methods focus on increasing diversity in language, topics, or dialogue acts at the utterance level, largely neglecting a critical aspect of task logic diversity at the dialogue level. This paper proposes a novel data augmentation method designed to enhance the diversity of synthetic dialogues by focusing on task execution logic. Our method uses LLMs to generate decision tree-structured task plans, which enables the derivation of diverse dialogue trajectories for a given task. Each trajectory, referred to as a "dialog flow", guides the generation of a multi-turn dialogue that follows a unique trajectory. We apply this method to generate a task-oriented dialogue dataset comprising 3,886 dialogue flows across 15 different domains. We validate the effectiveness of this dataset using the next action prediction task, where models fine-tuned on our dataset outperform strong baselines, including GPT-4. Upon acceptance of this paper, we plan to release the code and data publicly.

📄 PDF Abstract BibTeX arXiv:2410.14853

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversityLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service

2025-07-25 · Ming Gong, Xucheng Huang, Ziheng Xu, Vijayan K. Asari arxiv

High-quality dialogue is crucial for e-commerce customer service, yet traditional intent-based systems struggle with dynamic, multi-turn interactions. We present MindFlow+, a self-evolving dialogue agent that learns doma…

Reinforcement LearningResponse Generation

SE(3)-Stochastic Flow Matching for Protein Backbone Generation

2023-10-03 · Avishek Joey Bose, Tara Akhound-Sadegh, Guillaume Huguet, Kilian Fatras 외

The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel generative models of increasing modelin…

QDFlow: A Python package for physics simulations of quantum dot devices

2025-09-16 · Donovan L. Buterakos, Sandesh S. Kalantre, Joshua Ziegler, Jacob M. Taylor 외 arxiv

Recent advances in machine learning (ML) have accelerated progress in calibrating and operating quantum dot (QD) devices. However, most ML approaches rely on access to large, representative datasets designed to capture t…

HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks

2026-05-06 · Nandiraju Gireesh, Yuanliang Ju, Chaoyi Xu, Weiheng Liu 외 arxiv

Recent advances in generative models have shown promise in generating behavior plans for long-horizon, sparse reward tasks. While these approaches have achieved promising results, they often lack a principled framework f…

P2DFlow: A Protein Ensemble Generative Model with SE(3) Flow Matching

2024-11-26 · Yaowei Jin, Qi Huang, Ziyang Song, Mingyue Zheng 외

Biological processes, functions, and properties are intricately linked to the ensemble of protein conformations, rather than being solely determined by a single stable conformation. In this study, we have developed P2DFl…