Spaces:
Running
Running
Title
Browse files- README.md +1 -1
- app/src/content/article.mdx +1 -1
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
title: '
|
| 3 |
short_desc: 'Evaluating scientific reasoning using the card game Eleusis'
|
| 4 |
emoji: 📝
|
| 5 |
colorFrom: blue
|
|
|
|
| 1 |
---
|
| 2 |
+
title: 'Can LLMs Play the Game of Science?'
|
| 3 |
short_desc: 'Evaluating scientific reasoning using the card game Eleusis'
|
| 4 |
emoji: 📝
|
| 5 |
colorFrom: blue
|
app/src/content/article.mdx
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
title: "
|
| 3 |
subtitle: "Evaluating scientific reasoning and metacognition using the card game Eleusis reveals distinct scientist personalities in large language models"
|
| 4 |
description: "A benchmark for evaluating LLM scientific reasoning using the card game Eleusis, testing iterative hypothesis formation, calibration, and strategic experimentation."
|
| 5 |
authors:
|
|
|
|
| 1 |
---
|
| 2 |
+
title: "Can LLMs Play the Game of Science?"
|
| 3 |
subtitle: "Evaluating scientific reasoning and metacognition using the card game Eleusis reveals distinct scientist personalities in large language models"
|
| 4 |
description: "A benchmark for evaluating LLM scientific reasoning using the card game Eleusis, testing iterative hypothesis formation, calibration, and strategic experimentation."
|
| 5 |
authors:
|