Benjamin Turtel, Philipp Schoenegger, Danny Franklin
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present an outcome-driven fine-tuning framework that enhances the forecasting capabilities of large language models (LLMs) without relying on human-curated reasoning samples. Our method leverages model self-play to generate pairs of diverse reasoning trajectories and probabilistic forecasts for a set of diverse questions that resolve after the models' knowledge cutoff date. We then rank pairs of these reasoning traces by their distance to the actual outcomes before fine-tuning the model via Direct Preference Optimization (DPO). On a separate test set, our approach increases prediction accuracy of Phi-4 14B and DeepSeek-R1 14B by between 7--10\% over a base model and a DPO fine-tuned control model with randomized labels, bringing them on par with forecasting capabilities of much larger frontier models like GPT-4o.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.05253")
get_code_for_paper("2502.05253")
have("2502.05253")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.05253.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.05253)
Connect an agent — have() is free.