Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Adam1010
/
goodhart-gap-benchmark
like
0
English
benchmark
reasoning
multi-step
evaluation
llm-evaluation
goodhart
execution-vs-understanding
consensus
multi-model
License:
mit
Model card
Files
Files and versions
xet
Community
main
goodhart-gap-benchmark
91.2 MB
1 contributor
History:
4 commits
Adam1010
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
ca5e3d7
verified
9 days ago
data
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
9 days ago
results
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
9 days ago
.gitattributes
1.72 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
9 days ago
README.md
6.33 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
9 days ago
create_combined_dataset.py
7.18 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
9 days ago
evaluate.py
16 kB
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
9 days ago
generate_dataset.py
45.8 kB
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
9 days ago
requirements.txt
17 Bytes
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
9 days ago