相关论文: ZeFaV: Boosting Large Language Models for Zero-sho…

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with…

Clarification need prediction (CNP) is a key task in conversational search, aiming to predict whether to ask a clarifying question or give an answer to the current user query. However, current research on CNP suffers from the issues of…

Despite tremendous improvements in natural language generation, summarization models still suffer from the unfaithfulness issue. Previous work evaluates faithfulness either using models trained on the other tasks or in-domain synthetic…

Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large…

As the popularity of voice assistants continues to surge, conversational search has gained increased attention in Information Retrieval. However, data sparsity issues in conversational search significantly hinder the progress of supervised…

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their…

Incorporating language comprehension into robotic operations unlocks significant advancements in robotics, but also presents distinct challenges, particularly in executing spatially oriented tasks like pattern formation. This paper…

This paper describes the search for an alternative approach to the automatic categorization of camera trap images. First, we benchmark state-of-the-art classifiers using a single model for all images. Next, we evaluate methods combining…

Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users. However, new classes with completely unseen data distributions can stream across any device in a federated…

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…

Fact verification datasets are typically constructed using crowdsourcing techniques due to the lack of text sources with veracity labels. However, the crowdsourcing process often produces undesired biases in data that cause models to learn…

Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of…

Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, tables, passages, etc. Even Large Language Models (LLMs) like GPT-4 fall short in this task. To…

This paper investigates adapting Audio Large Language Models (ALLMs) for speaker verification (SV). We reformulate SV as an audio question-answering task and conduct comprehensive zero-shot evaluations on public benchmarks, showing that…

Despite significant interest in developing general purpose fact checking models, it is challenging to construct a large-scale fact verification dataset with realistic real-world claims. Existing claims are either authored by crowdworkers,…

Query expansion, pivotal in search engines, enhances the representation of user information needs with additional terms. While existing methods expand queries using retrieved or generated contextual documents, each approach has notable…

The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems…

Few-shot prompting elicits the remarkable abilities of large language models by equipping them with a few demonstration examples in the input. However, the traditional method of providing large language models with all demonstration…

Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples. Most studies on ZSL utilize side information such as…

Recent works have shown that unstructured text (documents) from online sources can serve as useful auxiliary information for zero-shot image classification. However, these methods require access to a high-quality source like Wikipedia and…