Related papers: Inter-Passage Verification for Multi-evidence Mult…

Multimodal information extraction (MIE) aims to extract structured information from unstructured multimedia content. Due to the diversity of tasks and settings, most current MIE models are task-specific and data-intensive, which limits…

In this article we address the problem of automatic answer checking in interactive learning systems that support mathematical notation. This problem consists of the problem of establishing identities in formal mathematical systems and hence…

Retrieval augmented generation (RAG) with large language models (LLMs) for Question Answering (QA) entails furnishing relevant context within the prompt to facilitate the LLM in answer generation. During the generation, inaccuracies or…

Question answering (QA) requires accurately aligning user questions with structured queries, a process often limited by the scarcity of high-quality query-natural language (Q-NL) pairs. To overcome this, we present Q-NL Verifier, an…

Most existing end-to-end Table Question Answering (Table QA) models consist of a two-stage framework with a retriever to select relevant table candidates from a corpus and a reader to locate the correct answers from table candidates. Even…

BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause incomparable scores for answers…

Multiple-Choice Question Answering (MCQA) is a challenging task in machine reading comprehension. The main challenge in MCQA is to extract "evidence" from the given context that supports the correct answer. In the OpenbookQA dataset, the…

Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the input length to LLMs grows linearly, causing a dramatic…

Knowledge-based visual question answering (KB-VQA) requires vision-language models to understand images and use external knowledge, especially for rare entities and long-tail facts. Most existing retrieval-augmented generation (RAG) methods…

The "Reason-Then-Respond" paradigm, enhanced by Reinforcement Learning, has shown great promise in advancing Multimodal Large Language Models. However, its application to the video domain has led to specialized models that excel at either…

We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well calibrated confidence scores for their results…

Despite significant progress in Visual Question Answering over the years, robustness of today's VQA models leave much to be desired. We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that…

Question answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with…

Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a reader reads top-ranking evidence to predict answers. According…

Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing…

Large language models often encounter challenges with static knowledge and hallucinations, which undermine their reliability. Retrieval-augmented generation (RAG) mitigates these issues by incorporating external information. However, user…

Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources. By jointly considering several sources like a knowledge base (KB), a text collection, and tables from the web, QA systems can…

Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark…

Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive…

Retrieval-augmented generation (RAG) improves large language model reliability by grounding generated responses in external evidence. However, RAG performance depends on the relevance of retrieved passages, the quality of evidence ranking,…