Related papers: Semantic Table Detection with LayoutLMv3
Document Understanding is an evolving field in Natural Language Processing (NLP). In particular, visual and spatial features are essential in addition to the raw text itself and hence, several multimodal models were developed in the field…
Legal passage retrieval is an important task that assists legal practitioners in the time-intensive process of finding relevant precedents to support legal arguments. This study investigates the task of retrieving legal passages or…
Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across…
Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretability, making it difficult for humans to understand predictions.…
LLMs have shown impressive progress in natural language processing. However, they still face significant challenges in TableQA, where real-world complexities such as diverse table structures, multilingual data, and domain-specific reasoning…
Temporal reasoning over tabular data presents substantial challenges for large language models (LLMs), as evidenced by recent research. In this study, we conduct a comprehensive analysis of temporal datasets to pinpoint the specific…
Database systems have to cater to the growing demands of the information age. The growth of the new age information retrieval powerhouses like search engines has thrown a challenge to the data management community to come up with novel…
Spreadsheet table detection is the task of detecting all tables on a given sheet and locating their respective ranges. Automatic table detection is a key enabling technique and an initial step in spreadsheet data intelligence. However, the…
Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual semantic arithmetic, inferring relationships from images,…
Document layout understanding is a field of study that analyzes the spatial arrangement of information in a document hoping to understand its structure and layout. Models such as LayoutLM (and its subsequent iterations) can understand…
Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning has shown remarkable progress in this realm, it typically requires an extensive dataset of…
Loop closure can effectively correct the accumulated error in robot localization, which plays a critical role in the long-term navigation of the robot. Traditional appearance-based methods rely on local features and are prone to failure in…
Large language models (LLMs) have exhibited an array of reasoning capabilities but face challenges like error propagation and hallucination, particularly in specialised areas like finance, where data is heterogeneous, and precision is…
Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…
Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been…
Large language models (LLMs) are becoming attractive as few-shot reasoners to solve Natural Language (NL)-related tasks. However, the understanding of their capability to process structured data like tables remains an under-explored area.…
Accurate localization and 3D maps are increasingly needed for various artificial intelligence based IoT applications such as augmented reality, intelligent transportation, crowd monitoring, robotics, etc. This article proposes a novel…
Predictive modeling on tabular data is the cornerstone of many real-world applications. Although gradient boosting machines and some recent deep models achieve strong performance on tabular data, they often lack interpretability. On the…
Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label alone is insufficient: it reveals little about the model's…
Large language models (LLMs) are increasingly used in situations where human values are at stake, such as decision-making tasks that involve reasoning when performed by humans. We investigate the so-called reasoning capabilities of LLMs…