English
Related papers

Related papers: DZ-TDPO: Non-Destructive Temporal Alignment for Mu…

200 papers

Text-to-audio (T2A) generation has advanced considerably in recent years, yet existing methods continue to face challenges in accurately rendering complex text prompts, particularly those involving intricate audio effects, and achieving…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-03 Yi Gu , Yanqing Liu , Chen Yang , Sheng Zhao

DPO and related algorithms align language models by directly optimizing the RLHF objective: find a policy that maximizes the Bradley-Terry reward while staying close to a reference policy through a KL divergence penalty. Previous work…

Machine Learning · Computer Science 2026-02-09 Idan Pipano , Shoham Sabach , Kavosh Asadi , Mohammad Ghavamzadeh

We present an approach to build Large Language Model (LLM) based slot-filling system to perform Dialogue State Tracking in conversational assistants serving across a wide variety of industry-grade applications. Key requirements of this…

Dialogue state tracking (DST) plays an essential role in task-oriented dialogue systems. However, user's input may contain implicit information, posing significant challenges for DST tasks. Additionally, DST data includes complex…

Computation and Language · Computer Science 2024-12-05 Zihao Yi , Zhe Xu , Ying Shen

Flow-Matching (FM)-based zero-shot text-to-speech (TTS) systems exhibit high-quality speech synthesis and robust generalization capabilities. However, the speaker representation ability of such systems remains underexplored, primarily due…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-18 Haoyu Li , Mingyang Han , Yu Xi , Dongxiao Wang , Hankun Wang , Haoxiang Shi , Boyu Li , Jun Song , Bo Zheng , Shuai Wang , Kai Yu

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a…

Computation and Language · Computer Science 2024-05-24 Cheng Niu , Xingguang Wang , Xuxin Cheng , Juntong Song , Tong Zhang

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Machine Learning · Computer Science 2026-04-13 Taojie Zhu , Dongyang Xu , Ding Zou , Sen Zhao , Qiaobo Hao , Zhiguo Yang , Yonghong He

Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based method selects a value…

Computation and Language · Computer Science 2020-10-29 Jian-Guo Zhang , Kazuma Hashimoto , Chien-Sheng Wu , Yao Wan , Philip S. Yu , Richard Socher , Caiming Xiong

This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive…

Computation and Language · Computer Science 2018-05-30 Nikola Mrkšić , Ivan Vulić

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is…

Computation and Language · Computer Science 2023-06-21 Haoning Zhang , Junwei Bao , Haipeng Sun , Youzheng Wu , Wenye Li , Shuguang Cui , Xiaodong He

Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be…

Computation and Language · Computer Science 2020-08-14 Qingkai Min , Libo Qin , Zhiyang Teng , Xiao Liu , Yue Zhang

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD),…

Computation and Language · Computer Science 2018-09-10 Victor Zhong , Caiming Xiong , Richard Socher

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different…

Computation and Language · Computer Science 2023-08-03 Qingyang Wu , James Gung , Raphael Shu , Yi Zhang

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses equally, neglecting the differing importance of individual…

Computation and Language · Computer Science 2026-05-27 Chengyu Huang , Zhuohang Li , Sheng-Yen Chou , Claire Cardie

Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating excessively long and redundant answers. For problems that exceed the model's capabilities,…

Machine Learning · Computer Science 2026-03-23 Yinan Xia , Haotian Zhang , Huiming Wang

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

Reinforcement learning has been central to recent advances in large language model reasoning, but most algorithms rely on on-policy training that demands fresh rollouts at every update, limiting efficiency and scalability. Asynchronous RL…

Machine Learning · Computer Science 2025-10-29 Haizhong Zheng , Jiawei Zhao , Beidi Chen

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

Computation and Language · Computer Science 2021-12-24 Xin Tian , Xinxian Huang , Dongfeng He , Yingzhan Lin , Siqi Bao , Huang He , Liankai Huang , Qiang Ju , Xiyuan Zhang , Jian Xie , Shuqi Sun , Fan Wang , Hua Wu , Haifeng Wang

Recently, researchers have explored using the encoder-decoder framework to tackle dialogue state tracking (DST), which is a key component of task-oriented dialogue systems. However, they regard a multi-turn dialogue as a flat sequence,…

Computation and Language · Computer Science 2021-07-27 Linhao Zhang , Houfeng Wang