相关论文: Answering Comparative Questions: Better than Ten-B…

We present an item-based approach for collaborative filtering. We determine a list of recommended items for a user by considering their previous purchases. Additionally other features of the users could be considered such as page views,…

Combinatorial optimization problems are computationally hard in general, but they are ubiquitous in our modern life. A coherent Ising machine (CIM) based on a multiple-pulse degenerate optical parametric oscillator (DOPO) is an alternative…

Multi-agent systems often require agents to collaborate with or compete against other agents with diverse goals, behaviors, or strategies. Agent modeling is essential when designing adaptive policies for intelligent machine agents in…

Was it fair that Harry was hired but not Barry? Was it fair that Pam was fired instead of Sam? How can one ensure fairness when an intelligent algorithm takes these decisions instead of a human? How can one ensure that the decisions were…

Recent advances in Multimodal Large Language Models (MLLMs) have shown impressive reasoning capabilities across vision-language tasks, yet still face the challenge of compute-difficulty mismatch. Through empirical analyses, we identify that…

We aim for mobile robots to function in a variety of common human environments. Such robots need to be able to reason about the locations of previously unseen target objects. Landmark objects can help this reasoning by narrowing down the…

Metric search commonly involves finding objects similar to a given sample object. We explore a generalization, where the desired result is a fair tradeoff between multiple query objects. This builds on previous results on complex queries,…

Without well-labeled ground truth data, machine learning-based systems would not be as ubiquitous as they are today, but these systems rely on substantial amounts of correctly labeled data. Unfortunately, crowdsourced labeling is time…

Large Language Models (LLMs) are rapidly reshaping information retrieval by enabling interactive, generative, and inference-driven search. While traditional keyword-based search remains central to web and academic information access, it…

Most recent state-of-the-art Visual Question Answering (VQA) systems are opaque black boxes that are only trained to fit the answer distribution given the question and visual content. As a result, these systems frequently take shortcuts,…

Evaluating competing systems in a comparable way, i.e., benchmarking them, is an undeniable pillar of the scientific method. However, system performance is often summarized via a small number of metrics. The analysis of the evaluation…

Fact-checking long-form text is challenging, and it is therefore common practice to break it down into multiple atomic claims. The typical approach to fact-checking these atomic claims involves retrieving a fixed number of pieces of…

The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets. Existing approaches for tackling this task leverage external knowledge…

Information Retrieval (IR) is the task of obtaining pieces of data (such as documents or snippets of text) that are relevant to a particular query or need from a large repository of information. While a combination of traditional keyword-…

A key capability in managing patent applications or a patent portfolio is comparing claims to other text, e.g. a patent specification. Because the language of claims is different from language used elsewhere in the patent application or in…

Large language models (LLMs) have demonstrated great potential for domain-specific applications, such as the law domain. However, recent disputes over GPT-4's law evaluation raise questions concerning their performance in real-world legal…

Search engines are the most commonly used type of tool for finding relevant information on the Internet. However, today's search engines are far from perfect. Typical search queries are short, often one or two words, and can be ambiguous…

In Conversational Recommendation Systems (CRS), a user provides feedback on recommended items at each turn, leading the CRS towards improved recommendations. Due to the need for a large amount of data, a user simulator is employed for both…

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's…

Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate query expansions…