Distilling an 8B reasoning teacher into a 0.6B student recovers most summary quality at ~50× speed, but teacher type—not scale alone—determines which capabilities transfer.
The curse of CoT: On the limitations of chain-of-thought in in-context learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
SciLens introduces an evidence-conditioned atomic entailment framework that grounds claims to modality-specific witnesses in tables and figures, achieving 79.2% macro-F1 on SciClaimEval.
citing papers explorer
-
Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment
Distilling an 8B reasoning teacher into a 0.6B student recovers most summary quality at ~50× speed, but teacher type—not scale alone—determines which capabilities transfer.
-
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding
SciLens introduces an evidence-conditioned atomic entailment framework that grounds claims to modality-specific witnesses in tables and figures, achieving 79.2% macro-F1 on SciClaimEval.