kjgpta/WhoDunIt-Evaluation_benchmark_for_culprit_detection_in_mystery_stories
WHODUNIT is a benchmark repository for evaluating large language models' deductive reasoning on mystery narratives. It provides a curated dataset of public domain mystery stories along with augmented variations to test model robustness under varied entity naming schemes.
No commits in the last 6 months.
Stars
3
Forks
—
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kjgpta/WhoDunIt-Evaluation_benchmark_for_culprit_detection_in_mystery_stories"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vectara/hallucination-leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
PKU-YuanGroup/Hallucination-Attack
Attack to induce LLMs within hallucinations
NishilBalar/Awesome-LVLM-Hallucination
up-to-date curated list of state-of-the-art Large vision language models hallucinations...
Amirhosein-gh98/Gnosis
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
intuit/sac3
Official repo for SAC3: Reliable Hallucination Detection in Black-Box Language Models via...