Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning
Paper
•
2505.24850
•
Published
•
8
•
3
Tongyan Hu
entropyhu
AI & ML interests
None yet
Recent Activity
authored
a paper
13 days ago
FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in
Finance Domain
upvoted
a
paper
14 days ago
FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in
Finance Domain
upvoted
a
paper
about 1 month ago
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP
Use
Organizations
commented
a
paper
5 months ago
Upload translated_low_gpt4o_hausa_1000.json
#2 opened 6 months ago
by
entropyhu
Upload inception_output_1000.json
#1 opened 6 months ago
by
entropyhu