论文 E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
论文 Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
论文 Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
论文 The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data
文档 flyP-on-Jay-2026-08-17
2026-08-17
论文 Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning