Related papers: User-in-the-loop Adaptive Intent Detection for Ins…
People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…
Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from compounding error, low sample efficiency, and high…
Agent assistance during human-human customer support spoken interactions requires triggering workflows based on the caller's intent (reason for call). Timeliness of prediction is essential for a good user experience. The goal is for a…
Domain experts possess tacit knowledge that they cannot easily articulate through explicit specifications. When experts modify AI-generated artifacts by correcting terminology, restructuring arguments, and adjusting emphasis, these edits…
Human intention-based systems enable robots to perceive and interpret user actions to interact with humans and adapt to their behavior proactively. Therefore, intention prediction is pivotal in creating a natural interaction with social…
Many approaches to Natural Language Processing (NLP) tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, human language is inherently…
Adaptive experiments automatically optimize their design throughout the data collection process, which can bring substantial benefits compared to conventional experimental settings. Potential applications include, among others: computerized…
Electric automation systems offer convenience and efficiency in controlling electrical circuits and devices. Traditionally, these systems rely on predefined commands for control, limiting flexibility and adaptability. In this paper, we…
Multi-modal intent detection aims to utilize various modalities to understand the user's intentions, which is essential for the deployment of dialogue systems in real-world scenarios. The two core challenges for multi-modal intent detection…
LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt…
Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…
The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational…
Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…
When we interact with small screen devices, sometimes we make errors, due to our abilities/disabilities, contextual factors that distract our attention or problems related to the interface. Recovering from these errors may be time consuming…
Intent detection is a critical component of task-oriented dialogue systems (TODS) which enables the identification of suitable actions to address user utterances at each dialog turn. Traditional approaches relied on computationally…
Assistive shared-control robots have the potential to transform the lives of millions of people afflicted with severe motor impairments. The usefulness of shared-control robots typically relies on the underlying autonomy's ability to infer…
Thanks to the rapid growth in wearable technologies and recent advancement in machine learning and signal processing, monitoring complex human contexts becomes feasible, paving the way to develop human-in-the-loop IoT systems that naturally…
Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's…
Although Large Language Models (LLMs) can generate coherent text, they often struggle to recognise user intent behind queries. In contrast, Natural Language Understanding (NLU) models interpret the purpose and key information of user input…
Recently, substantial research has been conducted on sequential recommendation, with the objective of forecasting the subsequent item by leveraging a user's historical sequence of interacted items. Prior studies employ both capsule networks…