Add comprehensive README
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- tool-use
|
| 5 |
+
- evaluation
|
| 6 |
+
- play2prompt
|
| 7 |
+
- stabletoolbench
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Play2Prompt (P2P) StableToolBench Evaluation Pipeline
|
| 11 |
+
|
| 12 |
+
Replicates the [Play2Prompt](https://aclanthology.org/2025.findings-acl.1347/) paper conditions on [StableToolBench](https://arxiv.org/abs/2403.07714) using Llama-3.1-8B-Instruct.
|
| 13 |
+
|
| 14 |
+
**Designed for extensibility**: The 4 conditions are controlled by two pluggable components — tool descriptions and in-context examples. To test your own description types, just drop replacement files into `p2p_data/descriptions/` and `p2p_data/examples/`.
|
| 15 |
+
|
| 16 |
+
See `pipeline/` directory for all source code.
|