#SciDaSynth
LightNews LightNews
infodocket.bsky.social
Updated Preprint: "SciDaSynth: Interactive Structured #Data Extraction from Scientific Literature with Large Language Model" arxiv.org/abs/2404.13765 #LLMs #AI
November 9, 2025 at 6:48 PM
bluesky.awakari.com
SciDaSynth: Interactive Structured Data Extraction from Sci Literature with LLM Article URL: https://onlinelibrary.wiley.com/doi/10.1002/cl2.70073 Comments URL: https://news.ycombinator.com/item?id=45863434 Points: 1 # Comments: 0

Interest | Match | Feed
Origin
onlinelibrary.wiley.com
November 9, 2025 at 6:52 AM
llms.activitypub.awakari.com.ap.brid.gy
SciDaSynth: Interactive Structured Data Extraction from Sci Literature with LLM Article URL: https://onlinelibrary.wiley.com/doi/10.1002/cl2.70073 Comments URL: https://news.ycombinator.com/item?id...

Origin | Interest | Match
Awakari App
awakari.com
November 9, 2025 at 6:52 AM
mehtarg.bsky.social
🤖 How SciDaSynth works - Powered by large language models, it answers user queries by pulling relevant information from diverse sources.
Generates ready‑to‑use data tables automatically.
Offers validation & refinement: visual summaries, semantic grouping, and cross‑document consistency checks.
November 4, 2025 at 4:50 AM
mehtarg.bsky.social
More details:
🚀 Introducing #SciDaSynth – an interactive system that lets researchers turn complex multimodal data — text, tables, figures — and scientific literature into structured data tables.

#CornellHumanEcology
@weillcornell.bsky.social
@cornelltech.bsky.social

doi.org/10.1002/cl2....
SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With Large Language Model
The explosion of scientific literature has made the efficient and accurate extraction of structured data a critical component for advancing scientific knowledge and supporting evidence-based decision...
doi.org
November 4, 2025 at 4:50 AM
mehtarg.bsky.social
Our paper on SciDaSynth: Interactive Structured Data Extraction From Scientific Literature With LLMs was just published in Campbell Collaboration Reviews. It was led by Xingbo Wang and Samantha L. Huey, PhD with Rui Sheng and was a collaboration between our team at @cpnh.bsky.social and Fei Wang.
System workflow of SciDaSynth: (1) Retrieval augmented generation (RAG) based technical framework for extracting and structuring data from figures, text, and tables in scientific documents using LLMs. (2) The user interface then allows for data extraction via question-answering, data validation, correction, summarization, standardization, and database updates through an iterative refinement process. User interface of SciDaSynth. The interfaces features: (A) A query panel for users to input natural language questions or select specific data attributes; (B) A data table displaying extracted information with highlighting of potentially problematic records; (C) Context menu options to validate data by examining relevant document snippets; (D) PDF viewer for accessing original sources; (E) Data standardization panel with multi-level and multi-faceted data summarization and standardization support.
November 4, 2025 at 4:50 AM