How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
Paper
•
2505.24273
•
Published
•
5
Junlin Wang
junlinw
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL
in Enhancing LLM Reasoning
upvoted
a
paper
about 2 months ago
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical
Consistency Checks
updated
a dataset
3 months ago
junlinw/hf_humaneval_infilling_data_3sets_all
Organizations
upvoted
2
papers
about 2 months ago
upvoted
an
article
5 months ago
Article
Back to The Future: Evaluating AI Agents on Predicting Future Events
-
- +5
•
49
upvoted
a
paper
over 1 year ago