Extracting structured information from documents or scientific papers is crucial for data sharing and retrieval. Recently, Large Language Model (LLM) has shown its impressive ability in text understanding and several tools based on LLM has been developed. However, it’s still difficult to find a universal and user-friendly tool for various practical extraction tasks. To address this challenge, we propose OmniExtract, an automatic data extraction tool with user-friendly configuration files which can adapt to various data extraction tasks. OmniExtract uses a prompt optimized engineering to improve prompt and obtain high performance, and it can support a comprehensive data extraction including text and tables. Evaluation results show that OmniExtract obtains a high accuracy over 80% for 3 datasets. Furthermore, two additional data extraction applications using OmniExtract have been provided, achieving an accuracy of 92.21% and an average F1 score of 0.83 respectively. The data reliability performance shows that OmniExtract is a valuable tool for database updating.
Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially reproduce population-level patterns, yet often fail to capture human-like diversity. Our analysis shows that static-profile agents exhibit stronger demographic separation and within-group compression than humans, a pattern consistent with identity essentialism: demographic labels can encourage models to treat group-average tendencies as individual traits, homogenizing responses within groups. We argue that this limitation arises from two related factors: sparse, static agent representations and the limited ability of prompt-only memory to persistently integrate experience. Inspired by complementary memory systems, we propose LifeMem, a longitudinal memory framework that combines structured life-event retrieval with agent-specific parametric memory for experience integration. Experiments on Add Health and Understanding Society with three LLMs show that LifeMem improves alignment with human data in terms of response distributions, overall and within-group diversity, and patterns of within-person response change across life stages. These findings highlight the value of longitudinal life-event memory for constructing more faithful and dynamically evolving social agents.
Hexi Wang, Yujia Zhou, Bangde Du et al.· 0 citations
This work introduces LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks and evaluates 18 recent general and legal-domain LLMs on LexRubric, showing that different models exhibit distinct capability profiles, and that open-ended legal tasks remain challenging for current LLMs.
Yifan Chen, Haitao Li, Yiran Hu et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
