paper-with-me

Papers

REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction

2025-02-24 · Omar Sharif, Joseph Gatto, Madhusudan Basak, Sarah M. Preum

Event argument extraction identifies arguments for predefined event roles in text. Traditional evaluations rely on exact match (EM), requiring predicted arguments to match annotated spans exactly. However, this approach fails for generative models like large language models (LLMs), which produce diverse yet semantically accurate responses. EM underestimates performance by disregarding valid variations, implicit arguments (unstated but inferable), and scattered arguments (distributed across a document). To bridge this gap, we introduce Reliable Evaluation framework for Generative event argument extraction (REGen), a framework that better aligns with human judgment. Across six datasets, REGen improves performance by an average of 23.93 F1 points over EM. Human validation further confirms REGen's effectiveness, achieving 87.67% alignment with human assessments of argument correctness.

📄 PDF Abstract BibTeX arXiv:2502.16838

Code (0)

등록된 구현이 없습니다.

Tasks

Event Argument Extractionvalid

Similar Papers 제목 키워드 기반

Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning

2025-10-16 · Hwiyeol Jo, Joosung Lee, Jaehone Lee, Sang-Woo Lee 외 arxiv

Evaluating generative models, such as large language models (LLMs), commonly involves question-answering tasks where the final answer is selected based on probability of answer choices. On the other hand, for models requ…

Question Answering

Heat Transfer Prediction for Methane in Regenerative Cooling Channels with Neural Networks

2019-07-24 · Günther Waxenegger-Wilfing, Kai Dresia, Jan Christian Deeken, Michael Oschwald

Methane is considered being a good choice as a propellant for future reusable launch systems. However, the heat transfer prediction for supercritical methane flowing in cooling channels of a regeneratively cooled combust…

Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models

2024-11-14 · Chutian Meng, Fan Ma, Jiaxu Miao, Chi Zhang 외

Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-ima…

Image Generation

Transduction of an immortalized olfactory ensheathing glia cell line with the green fluorescent protein (GFP) gene: evaluation of its neuroregenerative capacity as a proof of concept

2024-01-26 · N Plaza, D Simón, J Sierra, MT Moreno-Flores

Olfactory ensheathing glia (OEG) cells are known to foster axonal regeneration of central nervous system (CNS) neurons. Several lines of reversibly immortalized human OEG (ihOEG) have been previously established that ena…

Enabling Adoption of Regenerative Agriculture through Soil Carbon Copilots

2024-11-25 · Margaret Capetz, Swati Sharma, Rafael Padilha, Peder Olsen 외

Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic carbon (SOC) levels, thus improving soi…

Management