The Hallucination Tax of Reinforcement Finetuning
Paper
•
2505.13988
•
Published
•
8
Synthetic Unanswerable Math (SUM)
A collection of models and dataset from the paper "The Hallucination Tax of Reinforcement Finetuning".
-
-
lime-nlp/Synthetic_Unanswerable_Math
Viewer • Updated • 36.8k • 276 • 9 -
lime-nlp/Llama-3.1-8B-Instruct-SUM01
Updated • 4 -
lime-nlp/Llama-3.1-8B-Instruct-SUM00
Updated • 27 -
lime-nlp/Llama-3.1-8B-Instruct-SUM10
Updated • 2 -
lime-nlp/Llama-3.1-8B-Instruct-SUM30
Updated • 12 -
lime-nlp/Llama-3.1-8B-Instruct-SUM50
Updated • 11 -
lime-nlp/Qwen2.5-7B-SUM00
Updated • 2 -
lime-nlp/Qwen2.5-7B-SUM01
Updated • 4 -
lime-nlp/Qwen2.5-7B-SUM10
Updated • 8 -
lime-nlp/Qwen2.5-7B-SUM30
Updated -
lime-nlp/Qwen2.5-7B-SUM50
Updated • 7 -
lime-nlp/Qwen2.5-7B-Instruct-SUM00
Updated • 13 -
lime-nlp/Qwen2.5-7B-Instruct-SUM01
Updated • 22 -
lime-nlp/Qwen2.5-7B-Instruct-SUM10
Updated • 1 -
lime-nlp/Qwen2.5-7B-Instruct-SUM30
Updated • 9 -
lime-nlp/Qwen2.5-7B-Instruct-SUM50
Updated • 5 -
lime-nlp/Qwen2.5-Math-1.5B-SUM00
Updated • 3 -
lime-nlp/Qwen2.5-Math-1.5B-SUM01
Updated • 5 -
lime-nlp/Qwen2.5-Math-1.5B-SUM10
Updated • 5 -
lime-nlp/Qwen2.5-Math-1.5B-SUM30
Updated • 4 -
lime-nlp/Qwen2.5-Math-1.5B-SUM50
Updated • 5