Related papers: Multi-hop Reading Comprehension across Documents w…

Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and…

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while…

Multi-hop question answering over knowledge graphs remains computationally challenging due to the combinatorial explosion of possible reasoning paths. Recent approaches rely on expensive Large Language Model (LLM) inference for both entity…

Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs), resulting in the discovery of new facts. A new class of methods have been proposed to tackle this problem by aggregating path information. These…

Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architecture called the Reasoning Network (ReasoNet) for machine…

Using knowledge graphs to assist deep learning models in making recommendation decisions has recently been proven to effectively improve the model's interpretability and accuracy. This paper introduces an end-to-end deep learning model,…

This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. We present a method…

Graph convolution networks have recently garnered a lot of attention for representation learning on non-Euclidean feature spaces. Recent research has focused on stacking multiple layers like in convolutional neural networks for the…

Information retrieval and question answering from safety regulations are essential for automated construction compliance checking but are hindered by the linguistic and structural complexity of regulatory text. Many queries are multi-hop,…

Distantly supervised datasets for relation extraction mostly focus on sentence-level extraction, and they cover very few relations. In this work, we propose cross-document relation extraction, where the two entities of a relation tuple…

Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question. Previous approaches usually only calculate question-aware passage representation and ignore…

Various approaches have been proposed for providing efficient computational approaches for abstract argumentation. Among them, neural networks have permitted to solve various decision problems, notably related to arguments (credulous or…

Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains…

A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…

Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, extending this paradigm to graph learning remains underexplored. Graph data is inherently…

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information. To address this problem, it has been recently…

Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is…

Commonsense question answering (QA) requires background knowledge which is not explicitly stated in a given context. Prior works use commonsense knowledge graphs (KGs) to obtain this knowledge for reasoning. However, relying entirely on…

Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths. However,…