Related papers: ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Ze…

Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and…

Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training…

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is…

Current LLM-based driving agents that rely on unstructured plain-text memory suffer from low-precision scene retrieval and inefficient reflection. To address this limitation, we present RESPOND, a structured decision-making framework for…

MultiWOZ is a well-known task-oriented dialogue dataset containing over 10,000 annotated dialogues spanning 8 domains. It is extensively used as a benchmark for dialogue state tracking. However, recent works have reported presence of…

End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks…

Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compared to general text limit the practical utility of existing…

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it.…

Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between…

With the development of Natural Language Processing, Automatic question-answering system such as Waston, Siri, Alexa, has become one of the most important NLP applications. Nowadays, enterprises try to build automatic custom service…

Natural Language Generation (NLG) is a key component in a task-oriented dialogue system, which converts the structured meaning representation (MR) to the natural language. For large-scale conversational systems, where it is common to have…

A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This renders environmental state and progress towards completing a…

Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG). We explore the tasks of one-shot learning and zero-shot domain transfer with DILOG on SimDial and…

Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting…

End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD…

Large language model (LLM) agents have increasingly advanced service applications, such as booking flight tickets. However, these service agents suffer from unreliability in long-horizon tasks, as they often produce policy violations, tool…

Transformer-based pretrained language models (PLMs) offer unmatched performance across the majority of natural language understanding (NLU) tasks, including a body of question answering (QA) tasks. We hypothesize that improvements in QA…

Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few…