English
Related papers

Related papers: DORA: Toward Policy Optimization for Task-oriented…

200 papers

The adoption of pre-trained language models in task-oriented dialogue systems has resulted in significant enhancements of their text generation abilities. However, these architectures are slow to use because of the large number of trainable…

Computation and Language · Computer Science 2023-02-14 Radostin Cholakov , Todor Kolev

To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the…

Machine Learning · Computer Science 2015-08-17 Pei-Hao Su , David Vandyke , Milica Gasic , Dongho Kim , Nikola Mrksic , Tsung-Hsien Wen , Steve Young

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…

Computation and Language · Computer Science 2026-05-26 Michael Orme , Yanchao Yu , Zhiyuan Tan

Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts…

Computation and Language · Computer Science 2025-03-04 Wanyu Du , Song Feng , James Gung , Lijia Sun , Yi Zhang , Saab Mansour , Yanjun Qi

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Artificial Intelligence · Computer Science 2024-12-25 Jiacai Liu , Chaojie Wang , Chris Yuhao Liu , Liang Zeng , Rui Yan , Yiwen Sun , Yang Liu , Yahui Zhou

Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bidding (AIGB). Advertisers often have personalized objectives…

Artificial Intelligence · Computer Science 2026-01-22 Mingxuan Song , Yusen Huo , Bohan Zhou , Shenglin Yin , Zhen Xiao , Jieyi Long , Zhilin Zhang , Chuan Yu

Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language…

Computation and Language · Computer Science 2024-08-01 Xiang Luo , Zhiwen Tang , Jin Wang , Xuejie Zhang

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

Machine Learning · Computer Science 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang

Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Extensive research has focused on vision-to-language…

Computation and Language · Computer Science 2018-05-10 Jiaping Zhang , Tiancheng Zhao , Zhou Yu

This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…

Computation and Language · Computer Science 2022-09-13 Zhi Chen , Yuncong Liu , Lu Chen , Su Zhu , Mengyue Wu , Kai Yu

Task-oriented dialogues often require agents to enact complex, multi-step procedures in order to meet user requests. While large language models have found success automating these dialogues in constrained environments, their widespread…

Computation and Language · Computer Science 2023-06-08 Julia White , Arushi Raghuvanshi , Yada Pruksachatkun

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

Computation and Language · Computer Science 2026-01-12 Jiawei Shen , Jia Zhu , Hanghui Guo , Weijie Shi , Yue Cui , Qingyu Niu , Guoqing Ma , Yidan Liang , Jingjiang Liu , Yiling Wang , Shimin Di , Jiajie Xu

Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD). These approaches,…

Computation and Language · Computer Science 2022-05-24 Chia-Chien Hung , Anne Lauscher , Simone Paolo Ponzetto , Goran Glavaš

Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output vocabulary, e.g. in…

Computation and Language · Computer Science 2019-04-16 Tiancheng Zhao , Kaige Xie , Maxine Eskenazi

Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain…

Computation and Language · Computer Science 2020-11-17 Hung Le , Doyen Sahoo , Chenghao Liu , Nancy F. Chen , Steven C. H. Hoi

Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus on improving task-based conversational assistants online,…

Computation and Language · Computer Science 2021-10-06 Ruijie Zhou , Soham Deshmukh , Jeremiah Greer , Charles Lee

Robust state tracking for task-oriented dialogue systems currently remains restricted to a few popular languages. This paper shows that given a large-scale dialogue data set in one language, we can automatically produce an effective…

Computation and Language · Computer Science 2023-02-21 Mehrad Moradshahi , Victoria Tsai , Giovanni Campagna , Monica S. Lam

Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement…

Artificial Intelligence · Computer Science 2026-02-11 Kun Peng , Conghui Tan , Yu Liu , Guohua Tang , Zhongqian Sun , Wei Yang , Zining Zhu , Lei Jiang , Yanbing Liu , Hao Peng

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…

This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first…

Computation and Language · Computer Science 2019-09-06 Tho Luong Chi , Phuong Le-Hong