#math-benchmarks News & Analysis

2 articles tagged with #math-benchmarks. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Jun 16/10

🧠

Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation

Researchers identify Supervision Fidelity Decay (SFD) as a critical limitation in on-policy distillation where teacher model confidence deteriorates as student-generated reasoning chains lengthen. They propose Lookahead Group Reward (LGR) with entropy-triggered tree-attention to strengthen supervision signals, achieving 2.57-point improvements on math and code benchmarks, with gains reaching 4.92 points on AIME-26.

AINeutralarXiv – CS AI · May 126/10

🧠

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment

Researchers introduce TRACE, a novel training method that improves AI model performance by selectively applying different optimization techniques to critical versus routine tokens in reasoning tasks. The approach addresses inefficiencies in standard self-distillation by concentrating training effort on important decision points, achieving 2.76 percentage point improvements over baseline methods while better preserving out-of-distribution generalization.