Related papers: Model-Based Simulation for Optimising Smart Reply

Strictly proper scoring rules (SPSR) are incentive compatible for eliciting information about random variables from strategic agents when the principal can reward agents after the realization of the random variables. They also quantify the…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

Interactive user interfaces have increasingly explored AI's role in enhancing communication efficiency and productivity in collaborative tasks. The emergence of Large Language Models (LLMs) such as ChatGPT has revolutionized conversational…

Recommendation systems usually involve exploiting the relations among known features and content that describe items (content-based filtering) or the overlap of similar users who interacted with or rated the target item (collaborative…

Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations. A fundamental challenge in CRSs lies in effectively understanding user preferences from…

Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a…

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that…

Long-term user engagement (LTE) optimization in sequential recommender systems (SRS) is shown to be suited by reinforcement learning (RL) which finds a policy to maximize long-term rewards. Meanwhile, RL has its shortcomings, particularly…

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

Item (question) difficulties play a crucial role in educational assessments, enabling accurate and efficient assessment of student abilities and personalization to maximize learning outcomes. Traditionally, estimating item difficulties can…

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation. Existing methods select these subsets primarily using…

Large language Models (LLMs) are usually used to answer questions, but many high-stakes applications (e.g., tutoring, clinical support) require the complementary skill of asking questions: detecting missing information, requesting…

Automatic short answer scoring (ASAS) helps reduce the grading burden on educators but often lacks detailed, explainable feedback. Existing methods in ASAS with feedback (ASAS-F) rely on fine-tuning language models with limited datasets,…

Recent advancements in explainable recommendation have greatly bolstered user experience by elucidating the decision-making rationale. However, the existing methods actually fail to provide effective feedback signals for potentially better…

While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an…

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we…

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on…

Super-resolution (SR) is a promising tool for generating high-fidelity simulations of physical systems from low-resolution data, enabling fast and accurate predictions in engineering applications. However, existing deep-learning based SR…