arXiv Computation and Language

A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework

The paper introduces a scalable cross‑domain event extraction system built on a unified generative sequence‑to‑sequence framework. It jointly handles event detection and argument extraction, allowing both pipeline and end‑to‑end configurations. By fine‑tuning pretrained language models on multiple event datasets from diverse domains, the system retains domain‑specific semantics while generalizing across large, evolving label spaces, and offers a web‑based application for researchers to upload documents, extract events, visualize triggers and arguments, and compare configurations.

arXiv Computation and Language

Aug 25

A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction

The paper introduces a unified multi-domain and multi-task generative framework for event extraction that incorporates explicit domain conditioning signals and task-specific prompts. This design allows a single model to adapt dynamically to different event schemas without needing full event label sets during inference, supporting both pipeline and end-to-end extraction. Experiments on various benchmarks show competitive performance, strong cross-domain generalization, and practical scalability while maintaining domain-specific precision.

By Siting Liang, Omar Adjali, Daniel Sonntag

llms fine-tuning benchmarks

Hugging Face Trending Papers

Jul 30

From Single- to Cross-Document: Benchmarking Multi-Granularity Event Analysis of Large Language Models

Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks.

llms rag benchmarks

arXiv AI

2d ago

Automated Event Log Generation from Unstructured Text Using Finetuned LLMs

arXiv:2609.01320v1 Announce Type: new Abstract: Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM tec...

By Maximilian Seeth, Gabriel Marques Tavares, Daniel Schuster

llms fine-tuning

arXiv Computation and Language

3d ago

Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation

The paper introduces a configurable semantic chunking framework for biomedical information extraction in retrieval‑augmented generation systems. It replaces the fixed‑size chunking stage of BioMedRAG with entity‑preserving windows, trigger‑centered chunking, proposition‑first extraction, tiered trigger prioritization, and hierarchical relation resolution, while keeping the rest of the pipeline unchanged. Experiments on relation extraction benchmarks (GM‑CIHT, DDI, ChemProt) and adverse event classification (ADE) show that the hybrid configuration boosts performance on datasets with explicit relation cues, achieving 82.6% F1 on GM‑CIHT compared to 74.2% with the baseline.

By Riya Ahuja (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany), Tim Kacprowski (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany), Roya Shiasi Sardoabi (Institute of Data Science in Biomedicine, TU Braunschweig, Braunschweig, Germany, Braunschweig Integrated Centre of Systems Biology, TU Braunschweig, Braunschweig, Germany)

rag benchmarks

arXiv AI

Jun 2

Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems

arXiv:2606. 00282v1 Announce Type: cross Abstract: Large-scale recommendation systems operate across diverse domains, yet they face the challenges of data sparsity and noisy implicit feedback.

By Xiangyu Wang, Yawen He, Shivendra Pratap Singh, Han Huang, Mengtong Hu, Sharath Ciddu, Yi-Hsuan Hsieh, Erik Groving, Yi Ding, Jieming Di, Tony Wang, Min Yun, Xiaoyu Chen, Ling Leng, Rob Malkin

llms efficiency

arXiv Machine Learning

2d ago

Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs

arXiv:2609.00184v1 Announce Type: cross Abstract: Large language models (LLMs) rely on static pretraining corpora, causing their knowledge to become outdated over time. Existing approaches for evalua...

By Jonathan Zheng, Zirui Shao, Alan Ritter, Wei Xu

llms fine-tuning benchmarks

arXiv AI

Jun 3

Efficient Temporal Datalog Materialisation for Composite Event Recognition

arXiv:2605. 02488v2 Announce Type: replace Abstract: Several applications demand the timely detection of critical situations, such as threats to safety and transparency, over high-velocity streams of symbolic events.

By Periklis Mantenoglou

benchmarks safety

arXiv Machine Learning

Jul 27

SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text

arXiv:2607. 21610v1 Announce Type: cross Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available.

By Miaobo Hu, Xiaobo Guo, Shuhao Hu, Bokun Wang, Rui Chen, Xin Wang, Daren Zha, Jun Xiao

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 26

Evaluation Pitfalls and Challenges in Multimedia Event Extraction

arXiv:2606. 26775v1 Announce Type: cross Abstract: Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understanding.

By Philipp Seeberger, Steffen Freisinger, Tobias Bocklet, Korbinian Riedhammer

arXiv Machine Learning

Aug 12

Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety

arXiv:2512. 06227v3 Announce Type: replace-cross Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky behaviours for online safety, yet labelling such information is often costly and/or difficult due to its multi-label and dynamic nature.

By Junyu Mao, Anthony Hills, Talia Tseriotou, Maria Liakata, Aya Shamir, Dan Sayda, Dana Atzil-Slonim, Natalie Djohari, Pamela Ugwudike, Mahesan Niranjan, Stuart E. Middleton

llms nlp safety

arXiv Machine Learning

Aug 12

ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models

arXiv:2608. 10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to predict what happens while treating when it happens as a secondary concern.

By Adrien Schoen, Nachiketa Ratnakar Patil, Arjun Bhagoji, Francesco Bronzino

llms

arXiv AI

Jul 2

SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

arXiv:2607. 00008v1 Announce Type: cross Abstract: Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex.

By Sin Yu Bonnie Ho, Arlie Coles, Erik Larsson, Eric Marshall, Nathan Bodenstab, Paul Vozila

llms rag

Related stories