Related papers: AURA: A Reinforcement Learning Framework for AI-Dr…
AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can…
Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the…
As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of…
Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under…
Conversational agents, such as chatbots, have increasingly found their way into many dimensions of our lives, including entertainment and education. In this exploratory study we built a child-friendly chatbot, "Ask Me Anything" (AMA), and…
Recent advances in machine learning and artificial intelligence have provided more alternatives for the implementation of repetitive or monotonous tasks. However, the development of AI tools has not been straightforward, and use case…
Reinforcement Learning (RL)-based recommender systems have demonstrated promising performance in meeting user expectations by learning to make accurate next-item recommendations from historical user-item interactions. However, existing…
The use of reinforcement learning to dynamically adapt and evade detection is now well-documented in several cybersecurity settings including Covert Social Influence Operations (CSIOs), in which bots try to spread disinformation. While AI…
Reinforcement Learning (RL) is a powerful machine learning paradigm that has been applied in various fields such as robotics, natural language processing and game playing achieving state-of-the-art results. Targeted to solve sequential…
Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and…
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…
Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…
Access to mental health support remains limited, particularly in marginalized communities where structural and cultural barriers hinder timely care. This paper explores the potential of AI-enabled chatbots as a scalable solution, focusing…
The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…
Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…
To evaluate Large Language Models (LLMs) for question answering (QA), traditional methods typically focus on assessing single-turn responses to given questions. However, this approach doesn't capture the dynamic nature of human-AI…
Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off - particularly in domains that depend…
How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time,…
While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot explain why a response failed or how to adapt to dynamic user…
Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation…