# Foresight Learning for SEC Risk Prediction

arXiv: https://arxiv.org/abs/2601.19189 · HTML: https://mlsanity.com/paper/2601.19189/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 7 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 2 of 2)

- [Future-as-Label: Scalable Supervision from Real-World Outcomes](https://mlsanity.com/paper/2601.06336/) (2026)
- [The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications](https://mlsanity.com/paper/2511.08621/) (2025)

## Built on by (most cited first, 1 of 1)

- [Training Large Language Models to Predict Clinical Events](https://mlsanity.com/paper/2605.12817/) (2026)

## Abstract (arXiv)

Risk disclosures in SEC filings describe potential adverse events but rarely quantify their likelihood, limiting their usefulness for probabilistic analysis. A central obstacle is the absence of large-scale, risk-level supervision linking disclosed risks to realized outcomes. We introduce a fully automated data generation pipeline that converts qualitative SEC risk disclosures into temporally grounded supervision using only public data. For each filing, the pipeline generates firm-specific, time-bounded risk queries from the Risk Factors section and labels them by automatically resolving outcomes against subsequent disclosures. Using this dataset of risk queries and outcomes grounded in SEC filings, we train a compact large language model to estimate the probability that a disclosed risk will materialize within a specified horizon. Despite its modest size, the resulting model substantially improves over pretrained and heuristic baselines, and outperforms frontier general-purpose models, including GPT-5, on probabilistic accuracy and calibration. More broadly, this work demonstrates that Foresight Learning enables scalable and fully automated training of domain-specific expert models using only raw, chronological, in-domain text -- without proprietary data, external corpora, or manual annotation. The resulting models achieve frontier-level performance while remaining deployable on a single GPU. This result suggests a general pathway for learning calibrated, decision-relevant signals from naturally occurring enterprise documents. To support transparency and reproducibility, we open-source the evaluation dataset used in this study. Evaluation Data: https://huggingface.co/datasets/LightningRodLabs/sec_risk_questions_test_set Data Generation Platform: https://lightningrod.ai/ SDK: https://github.com/lightning-rod-labs/lightningrod-python-sdk