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 • 524 • 12 -
lime-nlp/Llama-3.1-8B-Instruct-SUM01
8B • Updated • 8 -
lime-nlp/Llama-3.1-8B-Instruct-SUM00
8B • Updated • 45 -
lime-nlp/Llama-3.1-8B-Instruct-SUM10
8B • Updated • 10 -
lime-nlp/Llama-3.1-8B-Instruct-SUM30
8B • Updated • 37 -
lime-nlp/Llama-3.1-8B-Instruct-SUM50
8B • Updated • 57 -
lime-nlp/Qwen2.5-7B-SUM00
8B • Updated • 8 -
lime-nlp/Qwen2.5-7B-SUM01
8B • Updated • 7 -
lime-nlp/Qwen2.5-7B-SUM10
8B • Updated • 27 -
lime-nlp/Qwen2.5-7B-SUM30
8B • Updated • 6 -
lime-nlp/Qwen2.5-7B-SUM50
8B • Updated • 27 -
lime-nlp/Qwen2.5-7B-Instruct-SUM00
8B • Updated • 29 -
lime-nlp/Qwen2.5-7B-Instruct-SUM01
8B • Updated • 44 -
lime-nlp/Qwen2.5-7B-Instruct-SUM10
8B • Updated • 5 -
lime-nlp/Qwen2.5-7B-Instruct-SUM30
8B • Updated • 27 -
lime-nlp/Qwen2.5-7B-Instruct-SUM50
8B • Updated • 7 -
lime-nlp/Qwen2.5-Math-1.5B-SUM00
2B • Updated • 129 -
lime-nlp/Qwen2.5-Math-1.5B-SUM01
2B • Updated • 9 -
lime-nlp/Qwen2.5-Math-1.5B-SUM10
2B • Updated • 7 -
lime-nlp/Qwen2.5-Math-1.5B-SUM30
2B • Updated • 405 -
lime-nlp/Qwen2.5-Math-1.5B-SUM50
2B • Updated • 7