Option Return Predictability via Large Language Models
A 2026 paper by Liu and co-authors on news sentiment and text signals in volatility and options, using a large language model: the abstract mentions alpha, t-statistics and an out-of-sample test and leaves out a benchmark, transaction costs, multiple testing and the size of the universe.
“We investigate the capabilities of Large Language Models (LLMs) in generating novel alpha factors for option returns.”
AssetVolatility and optionsoptions
StrategyNews sentimentmachine learning
TechniqueLarge language model
GeographyUSChina
Also stated: Alpha, t-statistic, Text and news, Order book, out-of-sample test
Missing from abstract: benchmark, costs, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodNews sentiment and text signals by year
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| DisclosureBeta: A Measurement-Channel Theory for Regime-Conditioned Betas from LLM-Read Risk Disclosures by Wong | 2026 | ||||
| Large Language Models and Futures Price Factors in China by Cheng et al. | 2025 | ||||
| Execution-Aware Alpha Mining: Teaching LLM Factor Agents to Account for Trading Costs by Nagireddy | 2026 | ||||
| The Economic Value of Sample Correlation Information in Minimum-Variance Portfolios by Liu and Liu | 2026 | ||||
| Memorisation or Alpha? Detecting Look-Ahead Contamination in Cross-Sectional Equity Signals by Nguyen | 2026 |