Related papers: AURA: A Reinforcement Learning Framework for AI-Dr…
Diagnostic errors in healthcare persist as a critical challenge, with increasing numbers of patients turning to online resources for health information. While AI-powered healthcare chatbots show promise, there exists no standardized and…
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, depend on…
Millions of users turn to consumer AI chatbots to discuss mental health and behavioral concerns. While this presents unprecedented opportunities to deliver population-level support, it also highlights an urgent need for rigorous and…
Modeling user behavior is critical across many industries where understanding preferences, intent, or decisions informs personalization, targeting, and strategic outcomes. Surveys have long served as a classical mechanism for collecting…
Evolutionary algorithms (EA), a class of stochastic search methods based on the principles of natural evolution, have received widespread acclaim for their exceptional performance in various real-world optimization problems. While…
Conversational shopping agents represent a critical consumer-facing application of Large Language Model (LLM)-powered agents, yet how to effectively apply post-training Reinforcement Learning (RL) to optimize such agents remains…
This white paper presents our work on SurveyLM, a platform for analyzing augmented language models' (ALMs) emergent alignment behaviors through their dynamically evolving attitude and value perspectives in complex social contexts. Social…
The attention for personalized mental health care is thriving. Research data specific to the individual, such as time series sensor data or data from intensive longitudinal studies, is relevant from a research perspective, as analyses on…
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled…
The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems,…
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to…
Response generation for task-oriented dialogues involves two basic components: dialogue planning and surface realization. These two components, however, have a discrepancy in their objectives, i.e., task completion and language quality. To…
Reinforcement Learning (RL) has become an effective paradigm for enhancing Large Language Models (LLMs) and visual generative models. However, its application in text-to-audio (TTA) generation remains largely under-explored. Prior work…
Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent…
There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely on self-reported user data or interviews, offering limited insights into real-time…
Mental health issues differ widely among individuals, with varied signs and symptoms. Recently, language-based assessments have shown promise in capturing this diversity, but they require a substantial sample of words per person for…
Conversational interfaces are currently on the rise: more and more applications rely on a chat-like interaction pattern to increase their acceptability and to improve user experience. Also in the area of questionnaire design and…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
In this work, we present a new dataset and a computational strategy for a digital coach that aims to guide users in practicing the protocols of self-attachment therapy. Our framework augments a rule-based conversational agent with a…
Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses…