Certain document automation scenarios, such as intelligent form infilling and privacy-strict parsing, require models to comprehend unpopulated templates. Yet existing benchmarks mainly use content-filled tables, leaving the template side of document understanding under-evaluated. To bridge this gap, we introduce NEST, a benchmark of 828 Native Empty Structural Templates from real-world, born-digital forms. NEST removes filled content while preserving complex hierarchical layouts and guided selection options in authentic administrative workflows. Through Structural Schema Parsing, Cell-Header Alignment, and Generative Infilling, NEST directly evaluates structural reasoning without content-based shortcuts. Experiments reveal a clear template–instance gap: state-of-the-art LLMs drop by 9.5 percentage points on average when evaluated on unpopulated templates rather than populated instances. We further show that Generative Infilling is a data-efficient tuning signal for template completion, raising infilling accuracy by 16.37 percentage points and the three-task average by 8.19 percentage points with only 662 (80%) training templates. NEST thus provides a benchmark for measuring template-level understanding and highlights a data-efficient route for improving template completion. The code, data, and results for this paper are available at https://github.com/cpeng-research/NEST-Benchmark.

Document-level event argument extraction (EAE) is a critical task in natural language processing. While most prior approaches rely on supervised training with large labeled datasets or resource-intensive fine-tuning, recent studies explore in-context learning (ICL) with LLMs to reduce data dependence and training costs. However, the performance of ICL-based methods still lags behind fully supervised models.We highlight a key reason for this shortfall: the lack of sufficient extraction rules. In this paper, we conduct a systematic study of using hierarchical rules to enhance LLMs’ ICL capabilities. We first define three types of hierarchical rules and demonstrate their effectiveness in enhancing the performance of LLMs for document-level EAE. Building on this, we further propose an LLM-driven HiErarchical Rule Optimization (HERO) framework that iteratively generates and selects optimal hierarchical rules. Specifically, in each iteration, high-value instances are selected to produce error feedback, which is used to update and expand hierarchical rule sets. This results in multiple candidate hierarchical rule sets, from which the optimal one is selected using a scoring-based mechanism. During inference, prompts are constructed using the optimal hierarchical rules to enhance ICL performance of LLMs. Extensive experiments demonstrate the effectiveness of HERO, surpassing few-shot supervised methods and outperforming state-of-the-art prompting baselines by 3.18% F1 on RAMS, 4.30% F1 on DocEE-N, and 3.17% F1 on DocEE-C.

“Biomedical event representation can be applied to various language tasks. A biomedical eventoften involves multiple biomedical entities and trigger words, and the event structure is complex.However, existing research on event representation mainly focuses on the general domain. Ifmodels from the general domain are directly transferred to biomedical event representation, theresults may not be satisfactory. We argue that biomedical events can be divided into three hierar-chies, each containing unique feature information. Therefore, we propose the Triple-views EventHierarchy Model (TEHM) to enhance the quality of biomedical event representation. TEHM ex-tracts feature information from three different views and integrates them. Specifically, due to thecomplexity of biomedical events, We propose the Trigger-aware Aggregator module to handlecomplex units within biomedical events. Additionally, we annotate two similarity task datasetsin the biomedical domain using annotation standards from the general domain. Extensive exper-iments demonstrate that TEHM achieves state-of-the-art performance on biomedical similaritytasks and biomedical event casual relation extraction.Introduction”