Spaces:
Sleeping
Sleeping
Siddh commited on
Update README.md by removing unnecessary metadata
Browse filesRemoved metadata and author information from README.
README.md
CHANGED
|
@@ -1,20 +1,7 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Context Corruption Env
|
| 3 |
-
emoji: 🔍
|
| 4 |
-
colorFrom: blue
|
| 5 |
-
colorTo: purple
|
| 6 |
-
sdk: docker
|
| 7 |
-
app_port: 7860
|
| 8 |
-
pinned: false
|
| 9 |
-
license: mit
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
# ContextCorruption-Env
|
| 13 |
|
| 14 |
> OpenEnv Hackathon | Meta x Hugging Face x PyTorch
|
| 15 |
|
| 16 |
-
**Submission by:** Siddh Sanghavi, Aagam Parekh
|
| 17 |
-
|
| 18 |
ContextCorruption-Env is an OpenEnv environment for training epistemic robustness in LLMs. The agent receives a factual question plus retrieved documents, some of which are deliberately corrupted. It must answer the question and flag unreliable sources.
|
| 19 |
|
| 20 |
This submission targets **Theme #3.1: World Modeling / Professional Tasks**. The environment simulates a partially observable information workspace where some evidence is trustworthy and some evidence lies.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ContextCorruption-Env
|
| 2 |
|
| 3 |
> OpenEnv Hackathon | Meta x Hugging Face x PyTorch
|
| 4 |
|
|
|
|
|
|
|
| 5 |
ContextCorruption-Env is an OpenEnv environment for training epistemic robustness in LLMs. The agent receives a factual question plus retrieved documents, some of which are deliberately corrupted. It must answer the question and flag unreliable sources.
|
| 6 |
|
| 7 |
This submission targets **Theme #3.1: World Modeling / Professional Tasks**. The environment simulates a partially observable information workspace where some evidence is trustworthy and some evidence lies.
|