Related papers: Lexical Learning as an Online Optimal Experiment: …
Interactive Machine Learning (IML) is an iterative learning process that tightly couples a human with a machine learner, which is widely used by researchers and practitioners to effectively solve a wide variety of real-world application…
Generating semantically coherent text requires a robust internal representation of linguistic structures, which traditional embedding techniques often fail to capture adequately. A novel approach, Latent Lexical Projection (LLP), is…
Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…
In this work, we present a novel human-in-the-loop framework to help the human user understand the decision making process that involves choosing preferred options. We focus on qualitative preference models over alternatives from…
Interactive Information Retrieval (IIR) and Reinforcement Learning (RL) share many commonalities, including an agent who learns while interacts, a long-term and complex goal, and an algorithm that explores and adapts. To successfully apply…
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose…
Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often…
The overarching goal of this work is to efficiently enable end-users to correctly anticipate a robot's behavior in novel situations. Since a robot's behavior is often a direct result of its underlying objective function, our insight is that…
Language User Interfaces (LUIs) could improve human-machine interaction for a wide variety of tasks, such as playing music, getting insights from databases, or instructing domestic robots. In contrast to traditional hand-crafted approaches,…
Ranking systems form the basis for online search engines and recommendation services. They process large collections of items, for instance web pages or e-commerce products, and present the user with a small ordered selection. The goal of a…
Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial human labor or time to gather such experiences for each task,…
Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby constructing stronger multi-agent systems (MAS). However,…
A significant part of human activity today consists of searching for a piece of information online, utilizing knowledge repositories. This endeavor may be time-consuming if the individual searching for the information is unfamiliar with the…
Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or extensive online interaction. In practice, acquiring…
Generalization to out of distribution tasks in reinforcement learning is a challenging problem. One successful approach improves generalization by conditioning policies on task or environment descriptions that provide information about the…
Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs…
Large Language Models (LLMs) have evolved from simple chatbots into sophisticated agents capable of automating complex real-world tasks, where browsing and reasoning over live web content is key to assessing retrieval and cognitive skills.…
People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…
Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language…
Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…