Related papers: DocTER: Evaluating Document-based Knowledge Editin…
Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions…
During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into their parameters. These parameterized facts enable realistic image generation, but they may become obsolete over time, thereby misrepresenting the…
The task of expert finding has been getting increasing attention in information retrieval literature. However, the current state-of-the-art is still lacking in principled approaches for combining different sources of evidence in an optimal…
Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing…
News articles usually contain knowledge entities such as celebrities or organizations. Important entities in articles carry key messages and help to understand the content in a more direct way. An industrial news recommender system contains…
We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a result of unintentional mistakes by content creators, our…
Robust model-editing techniques are essential for deploying large language models (LLMs) in practical applications, as they enable cost-effective ways to deal with challenges such as privacy breaches, bias mitigation and misinformation…
Recently, knowledge editing (KE) has emerged as a promising approach to update specific facts in Large Language Models (LLMs) without the need for full retraining. Despite the effectiveness in general-domain benchmarks, their applicability…
Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong editing. This study explores the fundamental reason why…
Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…
Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluate document understanding abilities, which significantly…
Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges.…
Resolving pronoun coreference requires knowledge support, especially for particular domains (e.g., medicine). In this paper, we explore how to leverage different types of knowledge to better resolve pronoun coreference with a neural model.…
Existing locate-then-edit Knowledge Editing (KE) methods typically decompose editing into two stages: upstream target representation optimization and downstream constrained parameter optimization. The optimization across the two stages is…
Recent evaluation protocols for Cross-document (CD) coreference resolution have often been inconsistent or lenient, leading to incomparable results across works and overestimation of performance. To facilitate proper future research on this…
Knowledge editing has emerged as a lightweight alternative to retraining for correcting or injecting specific facts in large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and…
Recent studies in prompting large language model (LLM) for document-level machine translation (DMT) primarily focus on the inter-sentence context by flatting the source document into a long sequence. This approach relies solely on the…
Document image classification is different from plain-text document classification and consists of classifying a document by understanding the content and structure of documents such as forms, emails, and other such documents. We show that…
Knowledge editing has emerged as an effective approach for updating large language models (LLMs) by modifying their internal knowledge. However, their application to the biomedical domain faces unique challenges due to the long-tailed…
As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at converting a set of knowledge triples into human readable sentences.…