A collection of models and dataset from the paper "The Hallucination Tax of Reinforcement Finetuning".
Language, Intelligence, and Model Evaluation Lab
non-profit
AI & ML interests
Natural Language Processing
Recent Activity
View all activity
Organization Card
LIME NLP is part of the USC NLP Group. Our team's primary focus is on creating trustworthy NLP models. We meticulously investigate the ethical consequences and broader societal effects of NLP models, striving to ensure that language technologies are constructed and employed in ways that align with ethical guidelines and uphold human values.
models
20
lime-nlp/Qwen2.5-Math-1.5B-SUM50
Updated
•
4
lime-nlp/Qwen2.5-Math-1.5B-SUM30
Updated
•
2
lime-nlp/Qwen2.5-Math-1.5B-SUM10
Updated
lime-nlp/Qwen2.5-Math-1.5B-SUM01
Updated
lime-nlp/Qwen2.5-Math-1.5B-SUM00
Updated
lime-nlp/Qwen2.5-7B-Instruct-SUM50
Updated
•
2
lime-nlp/Qwen2.5-7B-Instruct-SUM30
Updated
lime-nlp/Qwen2.5-7B-Instruct-SUM10
Updated
lime-nlp/Qwen2.5-7B-Instruct-SUM01
Updated
lime-nlp/Qwen2.5-7B-Instruct-SUM00
Updated
datasets
6
lime-nlp/Synthetic_Unanswerable_Math
Viewer
•
Updated
•
36.8k
•
226
•
7
lime-nlp/DeepScaleR_Difficulty
Viewer
•
Updated
•
5.06M
•
409
•
6
lime-nlp/orz_math_difficulty
Viewer
•
Updated
•
6.18M
•
249
lime-nlp/MATH_Difficulty
Viewer
•
Updated
•
1.61M
•
277
lime-nlp/GSM8K_Difficulty
Viewer
•
Updated
•
1.13M
•
187
lime-nlp/safer-instruct
Viewer
•
Updated
•
11.2k
•
90
•
1