LLM-Augmented Financial Networks Lift Quant Sharpe Ratio to 0.82
iblanco_finance · x · 2026-08-05
An arXiv paper proposes a two-stage framework: constructing a firm-level network from 10-K filings and then using an LLM to filter out spurious edges that lack genuine economic connections.
In a backtest on S&P 500 constituents (2011–2019), LLM-based edge filtering improved the long-short Sharpe ratio from 0.74 to 0.82 and reduced the max drawdown from -10.5% to -7.9%. The author notes this modest improvement is exactly the right size for a sane factor enhancement, suggesting LLMs should be used to clean inputs rather than invent trading signals.
More from Research
- AdaMAST: Boosting AI Agent Reliability via Failure Taxonomies — berkeley_ai · 2026-08-05
- Introducing Beckmann Transport Models: A New Framework for Generative Models — msalbergo · 2026-08-05
- Berkeley Paper Explores How Goal-Directed Mechanisms Affect AI and Human Behavior — berkeley_ai · 2026-08-05
- Multi-Agent Setups Can Cost 50x More, 79% of Failures Are Coordination Issues — Inevitable_Fee1895 · 2026-08-05
- NeurIPS 2026 Announces Inaugural Workshop on Diffusion Language Models — volokuleshov · 2026-08-05
- 12,160 Trials on GPT-5.4 Reveal Reproducible Cross-Script Artifact — rayanpal_ · 2026-08-05