Related papers: GEAR: Graph-based Evidence Aggregating and Reasoni…

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…

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could…

The modern digital world is highly heterogeneous, encompassing a wide variety of communications, devices, and services. This interconnectedness generates, synchronises, stores, and presents digital information in multidimensional, complex…

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…

Graph generative models become increasingly effective for data distribution approximation and data augmentation. While they have aroused public concerns about their malicious misuses or misinformation broadcasts, just as what Deepfake…

While Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in Large Language Models (LLMs), existing frameworks often falter on complex, multi-hop queries that require synthesizing information from disparate…

Increasing amounts of freely available data both in textual and relational form offers exploration of richer document representations, potentially improving the model performance and robustness. An emerging problem in the modern era is fake…

Visual Query Answering (VQA) is of great significance in offering people convenience: one can raise a question for details of objects, or high-level understanding about the scene, over an image. This paper proposes a novel method to address…

Fact-based Visual Question Answering (FVQA), a challenging variant of VQA, requires a QA-system to include facts from a diverse knowledge graph (KG) in its reasoning process to produce an answer. Large KGs, especially common-sense KGs, are…

Graph aggregation is the process of computing a single output graph that constitutes a good compromise between several input graphs, each provided by a different source. One needs to perform graph aggregation in a wide variety of…

Misinformation detection is a critical task that can benefit significantly from the integration of external knowledge, much like manual fact-checking. In this work, we propose a novel method for representing textual documents that…

Document-level Relation Extraction (DocRE) involves identifying relations between entities across multiple sentences in a document. Evidence sentences, crucial for precise entity pair relationships identification, enhance focus on essential…

Document-level relation extraction (DocRE) aims to extract relations between entities from unstructured document text. Compared to sentence-level relation extraction, it requires more complex semantic understanding from a broader text…

We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification. It challenges models to extract facts from several Wikipedia articles that are relevant to a claim and classify whether the claim is…

Visual question answering (Visual QA) has attracted significant attention these years. While a variety of algorithms have been proposed, most of them are built upon different combinations of image and language features as well as…

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,…

One challenge in fact checking is the ability to improve the transparency of the decision. We present a fact checking method that uses reference information in knowledge graphs (KGs) to assess claims and explain its decisions. KGs contain a…

Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect to the text. In this setting, always-on multimodal fusion wastes computation and can…

Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically requires multi-hop…

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA. This problem is most pronounced when answers can be found only by joining evidence from multiple documents. Curated knowledge…