Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text
Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliable supervision source for distillation. Building on programmatic distillation, we develop an approach that transfers reliable numerical reasoning from a large teacher model to a compact student using execution-verified Python programs instead of free-form textual rationales. It leverages gold deriva
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%rasbt/reasoning-from-scratch →
“Fuzzy title match (0.73): “Gold-Guided Programmatic Distillation for Financial Reasonin” ≈ “rasbt/reasoning-from-scratch””
- LinkedLinked via arxiv author · 85%Yun Dong →
“Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text”
- LinkedLinked via arxiv author · 85%Erica Zhao →
“Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text”
- LinkedLinked via arxiv author · 85%Elana Chen →
“Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text”