Related papers: Information Redundancy and Biases in Public Docume…

Knowledge Editing (KE) has gained increasing attention, yet current KE tasks remain relatively simple. Under current evaluation frameworks, many editing methods achieve exceptionally high scores, sometimes nearing perfection. However, few…

Instruction-following capabilities in LLMs have progressed significantly, enabling more complex user interactions through detailed prompts. However, retrieval systems have not matched these advances, most of them still relies on traditional…

Document-level Relation Extraction (DocRE) aims to identify relationships between entity pairs within a document. However, most existing methods assume a uniform label distribution, resulting in suboptimal performance on real-world,…

A standard model for exposing structured provenance metadata of scientific assertions on the Semantic Web would increase interoperability, discoverability, reliability, as well as reproducibility for scientific discourse and evidence-based…

Large-scale foundation models (FMs) in remote sensing (RS) are developed based on the paradigms established in computer vision (CV) and have shown promise for various Earth observation applications. However, the direct transfer of scaling…

This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and…

Multimodal document retrieval aims to identify and retrieve various forms of multimodal content, such as figures, tables, charts, and layout information from extensive documents. Despite its increasing popularity, there is a notable lack of…

Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn rich textual…

While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model…

In this paper, we identify an important reproducibility challenge in the image-to-set prediction literature that impedes proper comparisons among published methods, namely, researchers use different evaluation protocols to assess their…

Token repetition is a typical form of multi-modal problem in fully non-autoregressive translation (NAT). In this work, we revisit the multi-modal problem in recently proposed NAT models. Our study reveals that these advanced models have…

Transformer-based retrieval and reranking models for text document search are often refined through knowledge distillation together with contrastive learning. A tight distribution matching between the teacher and student models can be hard…

Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…

The Internet is integral to modern life, influencing communication, business, and lifestyles globally. As dependence on Internet services grows, the demand for high-quality service delivery increases. Service providers must maintain high…

This study investigates the position bias in information retrieval, where models tend to overemphasize content at the beginning of passages while neglecting semantically relevant information that appears later. To analyze the extent and…

Stepping from sentence-level to document-level, the research on relation extraction (RE) confronts increasing text length and more complicated entity interactions. Consequently, it is more challenging to encode the key information…

Memorization in large language models poses critical risks for privacy and fairness as these systems scale to billions of parameters. While previous studies established correlations between memorization and factors like token frequency and…

Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e., semantic entity), while the relations in-between are largely unexplored. In this paper, we…

We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…