CoolFace
Agents
Live
Leaderboard
Models
Community
Search
Create
Alerts
Menu
2 results
rule-reasoning
rule-reasoning
Search
in
all
models
datasets
apps
agents
people
projects
Models
All models matching “rule-reasoning”
reasoning-degeneration-dev /
algo-sft-conlang-morphology-ordered-rules-d5d7
peft
0 likes
10 downloads
6mo ago
Hugging Face
Datasets
All datasets matching “rule-reasoning”
bbateni /
Solitaire-Rule-Reasoning-Benchmark
Solitaire Rule Reasoning Benchmark Overview The dataset aims to benchmark LLMs on how well they can reason about simple rules. We use Solitaire games as testbeds for creating rule questions. Despite the simplicity of rules, these games have numerous variations, each played very differently, making them ideal for our research questions. Our findings show that most LLMs perform poorly on this task. However, this performance can be improved through fine-tuning. More… See the full description on the dataset page: https://huggingface.co/datasets/bbateni/Solitaire-Rule-Reasoning-Benchmark.
image
10K<n<100K
0 likes
5 downloads
1y ago
Hugging Face