Johannes Heidecke

2 papers on this site · 2022–2025

Johannes Heidecke has 2 papers on this site, in 2022–2025, most of them on Language models & pretraining; often with Alec Radford, Alex Beutel, Arvind Neelakantan.

The profile is the library's match of the name; two people with one name are not always told apart.

Topics

The most cited first (OpenAlex and our library).

Text and Code Embeddings by Contrastive Pre-Training (2022 · 316 citations)
Text embeddings power semantic search, classification and similarity scoring. In earlier work, each use case usually got its own dataset, training objective and architecture, and sentence-embedding research developed separately from neural retrieval. This OpenAI paper shows that one simple recipe can produce…
HealthBench: Evaluating Large Language Models Towards Improved Human Health (2025 · 115 citations)
Most medical benchmarks for LLMs use multiple-choice or short-answer questions. These capture little of how people actually seek health help, are rarely checked against expert judgment, and are often close to saturated. HealthBench, from OpenAI, addresses this with 5,000 realistic single- and multi-turn health…

4 more works of theirs are in our library without a page here yet; they will appear as we publish them.

12 of 14 co-authors with a page, the most papers together first.

Papers of our library cite their works 4 332 times (of the 140 884 papers whose bibliographies we read); 156 citing papers with a page here →.