Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.
-
Updated
May 2, 2026 - Python
Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.
AI analyst for SEC 10-K filings. RAG + LangGraph agent + GRPO fine-tuning on FinQA. 11.5% → 20.5% accuracy progression.
FinanceBench financial-report RAG with FAISS, Flask, Ragas, and financial numeric accuracy evaluation
Domain-adapted financial QA with NVIDIA NIM + NeMo LoRA fine-tuning. 126% Exact Match improvement on FinanceBench. Built with NVIDIA DLI course workflow.
Self-improving financial-QA agent on FinQA: a governed loop that refines its own prompt + reasoning level over 3 cycles (no retraining), with a validation-guarded gate that verifies every change on held-out data.
Controlled study: does continued pre-training on SEC 10-K filings help downstream financial QA? A clean negative result on a fair evaluation instrument. Qwen2.5-3B; FinQA/TAT-QA; CPT (LoRA and full-parameter), SFT, DPO.
Evidence-first Vietnamese financial QA with auditable retrieval, grounded plans, and safe Text-to-Pandas execution
FastAPI + LangGraph service for traceable financial QA over text and table inputs.
To associate your repository with the financial-qa topic, visit your repo's landing page and select "manage topics."