Towards Expert Financial QA via Self-Improving RAG
cs.CL
Submitted: 2026-08-27
Updated: 2026-09-23
Comments: 17 pages, 2 figures. Accepted at the ICLR 2026 Workshop on Advances in Financial AI
Code: https://github.com/D-Star-AI/dsRAG
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- FinanceBench: A New Benchmark for Financial Question Answering
- Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity
- Training Language Models to Self-Correct via Reinforcement Learning
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
- Self-Refine: Iterative Refinement with Self-Feedback
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
- VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Corrective Retrieval Augmented Generation
- Agent-as-a-Judge: Evaluate Agents with Agents
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering