Related papers: Large-scale Hybrid Approach for Predicting User Sa…
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…
Generative AI (GenAI) chatbots are becoming increasingly integrated into virtual assistant technologies, yet their success hinges on the ability to gather meaningful user feedback to improve interaction quality, system outcomes, and overall…
The prospect of combining human operators and virtual agents (bots) into an effective hybrid system that provides proper customer service to clients is promising yet challenging. The hybrid system decreases the customers' frustration when…
Predicting user satisfaction in conversational systems has become critical, as spoken conversational assistants operate in increasingly complex domains. Online satisfaction prediction (i.e., predicting satisfaction of the user with the…
Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…
Conversational information access is an emerging research area. Currently, human evaluation is used for end-to-end system evaluation, which is both very time and resource intensive at scale, and thus becomes a bottleneck of progress. As an…
Conversational agents have been gaining increasing popularity in recent years. Influenced by the widespread adoption of task-oriented agents such as Apple Siri and Amazon Alexa, these agents are being deployed into various applications to…
Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale…
Interactive AI systems, such as recommendation engines and virtual assistants, commonly use static user profiles and predefined rules to personalize interactions. However, these methods often fail to capture the dynamic nature of user…
In the realm of autonomous vehicles, dynamic user preferences are critical yet challenging to accommodate. Existing methods often misrepresent these preferences, either by overlooking their dynamism or overburdening users as humans often…
Balancing user agency and system automation is essential for effective human-AI interactions. Fully automated systems can deliver efficiency but risk undermining usability and user autonomy, while purely manual tools are often inefficient…
Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has primarily focused on enhancing either the recommendation…
When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feedback. Human feedback is the gold standard, particularly for…
Designing and evaluating personalized and proactive assistant agents remains challenging due to the time, cost, and ethical concerns associated with human-in-the-loop experimentation. Existing Human-Computer Interaction (HCI) methods often…
Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…
With the large language model showing human-like logical reasoning and understanding ability, whether agents based on the large language model can simulate the interaction behavior of real users, so as to build a reliable virtual…
Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…
Technology acceptance models effectively predict how users will adopt new technology products. Traditional surveys, often expensive and cumbersome, are commonly used for this assessment. As an alternative to surveys, we explore the use of…
Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…
Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative…