Related papers: Know Thy Strengths: Comprehensive Dialogue State T…

Domain generalization (DG) aims to improve the generalization ability of the model trained on several known training domains over unseen test domains. Previous work has shown that self-supervised contrastive pre-training improves the…

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…

Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the…

Discourse analysis allows us to attain inferences of a text document that extend beyond the sentence-level. The current performance of discourse models is very low on texts outside of the training distribution's coverage, diminishing the…

Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades…

Goal-oriented dialogue systems typically rely on components specifically developed for a single task or domain. This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to…

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach…

Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown: the model "loses the thread" mid-reasoning. We study whether such breakdowns…

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured…

The rapid proliferation of generative AI, especially large language models, has led to their integration into a variety of applications. A key phenomenon known as weak-to-strong generalization - where a strong model trained on a weak…

Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses. Recent studies on constrained Markov Bayesian polynomial (CMBP) framework take the first step towards bridging the gap…

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the…

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained…

Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive…

Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in terms of intents and slots contained in task-specific…

As an essential component in task-oriented dialogue systems, dialogue state tracking (DST) aims to track human-machine interactions and generate state representations for managing the dialogue. Representations of dialogue states are…

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains,…

Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, despite recent progress in domain adaptation, their reliance on in-domain data still limits their cross-domain scalability. In…

Previous works on depression detection use datasets collected in similar environments to train and test the models. In practice, however, the train and test distributions cannot be guaranteed to be identical. Distribution shifts can be…

Dialogue state tracking (DST) is an important step in dialogue management to keep track of users' beliefs. Existing works fine-tune all language model (LM) parameters to tackle the DST task, which requires significant data and computing…