相关论文: Multi-Step Reasoning Over Unstructured Text with B…
This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources…
Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries, and accurately retrieving essential…
Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…
Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities,…
Addressing the complexity of comprehensive information retrieval, this study introduces an innovative, iterative retrieval-augmented generation system. Our approach uniquely integrates a vector-space driven re-ranking mechanism with…
General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis…
Advances in natural language processing tasks have gained momentum in recent years due to the increasingly popular neural network methods. In this paper, we explore deep learning techniques for answering multi-step reasoning questions that…
Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document chunks. While effective for unstructured text, this approach is less reliable on…
Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to…
Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present…
Retrieval-Augmented Generation (RAG) systems often struggle with imperfect retrieval, as traditional retrievers focus on lexical or semantic similarity rather than logical relevance. To address this, we propose \textbf{HopRAG}, a novel RAG…
Information retrieval has transitioned from standalone systems into essential components across broader applications, with indexing efficiency, cost-effectiveness, and freshness becoming increasingly critical yet often overlooked. In this…
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps…
Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently…
Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have incorporated…
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging. This paper introduces an IR…
Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two…
Knowledge-Intensive Visual Question Answering (KI-VQA) refers to answering a question about an image whose answer does not lie in the image. This paper presents a new pipeline for KI-VQA tasks, consisting of a retriever and a reader. First,…
Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks. While retrieval-augmented frameworks traditionally focus on selecting top-ranked…
Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this,…