Collection of models and datasets for Beyond Binary Rewards: Training LMs to Reason about their Uncertainty
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated
a dataset
about 1 hour ago
mehuldamani/big-math-tough
published
a dataset
about 1 hour ago
mehuldamani/big-math-tough
published
a model
about 23 hours ago
mehuldamani/rlcr_single_from_rlvr_chkpt480
Organizations
None yet
models
196
mehuldamani/rlcr_single_from_rlvr_chkpt480
Updated
mehuldamani/rlvr-base-trainRlcr-ConfMoreOne_fracAcc_entroRew_pt5Brier_pt9Temp_reasonInPrompt
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_k_2
Updated
mehuldamani/qwen3_8b_medical_rlvr_multi_k_4
Updated
mehuldamani/rlvr-base-train-with-rlcr-sumConfMoreOne_fractAcc_pt5Brier_pt9Temp_reasonUncertInPrompt
Updated
mehuldamani/rlcr-multi-from-rlvr-base-sumConfMoreThanOne_pt5Brier-pt9Temp-specifyConf_reasonUncertInPrompt
Updated
mehuldamani/rlcr-multi-from-rlvr-base-train-1pointBrier-point9Temp-specifyConf_reasonUncertInPrompt
Updated
mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier-1point4Temp-specifyConfSumLessThan1
Updated
mehuldamani/rlcr-multi-from-rlvr-base-train-1pointBrier-point9Temp-specifyConfSumLessThan1
Updated
mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier-point9Temp-specifyConfSumLessThan1
Updated
datasets
50
mehuldamani/big-math-tough
Viewer
•
Updated
•
18.5k
mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlcr
Viewer
•
Updated
•
5k
•
10
mehuldamani/medTroubleshootig-rlvr-220-evaled-on-rlvr
Viewer
•
Updated
•
5k
•
10
mehuldamani/medDataset_25k
Viewer
•
Updated
•
75k
•
336
mehuldamani/medDataset
Viewer
•
Updated
•
1.29M
•
102
mehuldamani/qwen3_8b_ambigQA_rlcr_multi_analysis
Viewer
•
Updated
•
2k
•
17
mehuldamani/qwen3_8b_ambigQA_rlcr_single_passk_tryAgain
Viewer
•
Updated
•
2k
•
10
mehuldamani/ambigQA
Viewer
•
Updated
•
12k
•
77
mehuldamani/judge-new-sft-instruct
Viewer
•
Updated
•
100
•
3
mehuldamani/judge-new-sft-base
Viewer
•
Updated
•
100
•
7