Moderate evidence
Published recordScienceGood Space
More
New Large Language Models Outperform Older Models and Hallucinate Less in Operative Note Data Extraction
- Truvace record
- TRV-2026-2961raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 545ae74af895…check it
Background: Recent improvements in large language models (LLMs) may provide a scalable solution for registry data curation. However, trust in model outputs remains limited by hallucinations, wherein models invent information. Given the rapid pace of LLM development, the purpose of this study was to compare the accuracy and hallucination rates of a "newer" and an "older" and previously evaluated LLM in extracting total hip arthroplasty (THA) operative variables. Methods: Surgical approach, fixation technique, and…
The gain
In a study of 1,000 total hip arthroplasty operative notes, a 2026 language model extracted surgical approach, fixation and bearing surface at 98%, 98% and 93% accuracy versus 96%, 96% and 89% for a 2024 model, and hallucinated far less.
What this doesn’t fix
The authors say hallucinations persisted in the newer model, at 5%, 3% and 11% across the three tasks, which limits trustworthiness of its output.
Sources
1 on file- The Journal of Arthroplastydoi:10.1016/j.arth.2026.11.047
Cite this record
v1Truvace Impact Record TRV-2026-2961, v1: “New Large Language Models Outperform Older Models and Hallucinate Less in Operative Note Data Extraction.” Truvace, 2026-11-16. /record/TRV-2026-2961 (accessed on the day you copy it). sha256 545ae74af89573bf…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2961 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace