Continual dialogue state tracking via reason-of-select distillation

Y Feng, B Liu, X Dong, Z Lu, LM Zhan, A Lam… - arxiv preprint arxiv …, 2024 - arxiv.org
An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks
while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often …

Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation

T Zhang, C Huang, Y Deng, H Liang, J Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
We investigate non-collaborative dialogue agents, which are expected to engage in
strategic conversations with diverse users, for securing a mutual agreement that leans …

Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues

T He, L Liao, Y Cao, Y Liu, Y Sun, Z Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advancements in proactive dialogues have garnered significant attention,
particularly for more complex objectives (eg emotion support and persuasion). Unlike …

Sparse Rewards Can Self-Train Dialogue Agents

BM Lattimer, V Gangal, R McDonald, Y Yang - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents,
especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning …

Active Utterance Collection Based on Multi-armed Bandits for Natural Language Understanding in Dialog Systems

R Yang, K Wakabayashi - … Conference on Information Integration and Web …, 2025 - Springer
Training natural language understanding (NLU) models for dialog systems requires
collecting user utterances as training data. Unlike general classification or sequence …

[PDF][PDF] Dynamic Prompting: Large Language Models for Task Oriented Dialog

J Nehring, A Juneja, A Ahmad, R Roller, D Klakow - 2024 - ceur-ws.org
Abstract Large Language Models show impressive results in many different applications,
most notably in the context of questionanswering and open dialog situations. However, it is …

Automated Construction of Chain-of-Thought in Task-Oriented Dialogue Systems

M Ren, Y Wu, F Peng - 2024 6th International Conference on …, 2024 - ieeexplore.ieee.org
Large language models play a pivotal role in addressing human problem-solving
challenges, particularly in the context of dialogue systems where they are employed to …