相关论文: GEAR: Graph-based Evidence Aggregating and Reasoni…

In this paper we present our system for the FEVER Challenge. The task of this challenge is to verify claims by extracting information from Wikipedia. Our system has two parts. In the first part it performs a search for candidate sentences…

Despite recent success in natural language processing (NLP), fact verification still remains a difficult task. Due to misinformation spreading increasingly fast, attention has been directed towards automatically verifying the correctness of…

Fact-checking long-form text is challenging, and it is therefore common practice to break it down into multiple atomic claims. The typical approach to fact-checking these atomic claims involves retrieving a fixed number of pieces of…

Structured information about entities is critical for many semantic parsing tasks. We present an approach that uses a Graph Neural Network (GNN) architecture to incorporate information about relevant entities and their relations during…

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on…

This extended abstract introduces Self-Explaining Contrastive Evidence Re-Ranking (CER), a novel method that restructures retrieval around factual evidence by fine-tuning embeddings with contrastive learning and generating token-level…

Recently Graph Neural Network (GNN) has been applied successfully to various NLP tasks that require reasoning, such as multi-hop machine reading comprehension. In this paper, we consider a novel case where reasoning is needed over graphs…

Misinformation in healthcare, from vaccine hesitancy to unproven treatments, poses risks to public health and trust in medical systems. While machine learning and natural language processing have advanced automated fact-checking, validating…

The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we…

Fact-checking the truthfulness of claims usually requires reasoning over multiple evidence sentences. Oftentimes, evidence sentences may not be always self-contained, and may require additional contexts and references from elsewhere to…

Knowledge Graphs (KGs) store structured factual knowledge by linking entities through relationships, crucial for many applications. These applications depend on the KG's factual accuracy, so verifying facts is essential, yet challenging.…

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and information integrity. This motivates detectors that are not…

Energy-based models for discrete domains, such as graphs, explicitly capture relative likelihoods, naturally enabling composable probabilistic inference tasks like conditional generation or enforcing constraints at test-time. However,…

Collaborative graph analysis across multiple institutions is becoming increasingly popular. Realistic examples include social network analysis across various social platforms, financial transaction analysis across multiple banks, and…

Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of class probabilities that vary with the depth of the…

Machine Learning (ML) systems are a building part of the modern tools which impact our daily life in several application domains. Due to their black-box nature, those systems are hardly adopted in application domains (e.g. health, finance)…

Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG…

Given the widespread dissemination of misinformation on social media, implementing fact-checking mechanisms for online claims is essential. Manually verifying every claim is very challenging, underscoring the need for an automated…