Built on

Controlling the false discovery rate: a practical and powerful approach to multiple testing
Y. Benjamini and Y. Hochberg · 1995
Earlier work this paper cites.
Superforecasting: The art and science of prediction
P. E. Tetlock and D. Gardner · 2016
Earlier work this paper cites.
Mastering chess and shogi by self-play with a general reinforcement learning algorithm, 2017
Original
D. Silver, T. Hubert, J. Schrittwieser, I. Antonoglou, M. Lai, A. Guez, and D. Hassabis · 2017
Earlier work this paper cites.
Structured analytic techniques for intelligence analysis
R. H. Pherson and R. J. Heuer · 2019
Earlier work this paper cites.
Measuring mathematical problem solving with the math dataset, 2021
Original
D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, and J. Steinhardt · 2021
Earlier work this paper cites.
Show your work: Scratchpads for intermediate computation with language models, 2021
Original
M. Nye, A. J. Andreassen, G. Gur-Ari, H. Michalewski, J. Austin, D. Bieber, and A. Odena · 2021
Earlier work this paper cites.
Autocast++: Enhancing world event prediction with zero-shot ranking-based context retrieval, 2023
Original
Q. Yan, R. Seraj, J. He, L. Meng, and T. Sylvain · 2023
Earlier work this paper cites.
Gpqa: A graduate-level google-proof q&a benchmark, 2023
Original
D. Rein, B. L. Hou, A. C. Stickland, J. Petty, R. Y. Pang, J. Dirani, and S. R. Bowman · 2023
Earlier work this paper cites.
Nash learning from human feedback, 2023
Original
R. Munos, M. Valko, D. Calandriello, M. G. Azar, M. Rowland, Z. D. Guo, Y. Tang, M. Geist, T. Mesnard, C. Fiegel, A. Michi, M. Selvi, S. Girgin, N. Momchev, O. Bachem, D. J. Mankowitz, D. Precup, and B. Piot · 2023
Earlier work this paper cites.

Similar

Expertprompting: Instructing large language models to be distinguished experts, 2023
Original
B. Xu, A. Yang, J. Lin, Q. Wang, C. Zhou, Y. Zhang, and Z. Mao · 2023
Cited alongside, same era.
Forecastbench: A dynamic benchmark of ai forecasting capabilities, 2024
Original
E. Karger, H. Bastani, C. Yueh-Han, Z. Jacobs, D. Halawi, F. Zhang, and P. E. Tetlock · 2024
Cited alongside, same era.
Financial statement analysis with large language models, 2024
Original
A. Kim, M. Muhn, and V. Nikolaev · 2024
Cited alongside, same era.
From news to forecast: Integrating event analysis in llm-based time series forecasting with reflection, 2024
Original
X. Wang, M. Feng, J. Qiu, J. Gu, and J. Zhao · 2024
Cited alongside, same era.

Then

Direct preference optimization: Your language model is secretly a reward model
R. Rafailov, A. Sharma, E. Mitchell, C. D. Manning, S. Ermon, and C. Finn · 2024
Later among the works it cites.
Is dpo superior to ppo for llm alignment? a comprehensive study, 2024
Original
S. Xu, W. Fu, J. Gao, W. Ye, W. Liu, Z. Mei, and Y. Wu · 2024
Later among the works it cites.
Phi-4 technical report, 2024
Original
M. Abdin, J. Aneja, H. Behl, S. Bubeck, R. Eldan, S. Gunasekar, and Y. Zhang · 2024
Later among the works it cites.
Gpt-4o system card, 2024
Original
A. Hurst, A. Lerer, A. P. Goucher, A. Perelman, A. Ramesh, A. Clark, and I. Kivlichan · 2024
Later among the works it cites.
Qwen2.5 technical report, 2024
Original

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

LLMs Can Teach Themselves to Better Predict the Future

Turtel, Benjamin, Franklin, Danny, Schoenegger, Philipp

Understand

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.

Built on

Controlling the false discovery rate: a practical and powerful approach to multiple testing
Y. Benjamini and Y. Hochberg · 1995
Earlier work this paper cites.
Superforecasting: The art and science of prediction
P. E. Tetlock and D. Gardner · 2016
Earlier work this paper cites.
Mastering chess and shogi by self-play with a general reinforcement learning algorithm, 2017
Original
D. Silver, T. Hubert, J. Schrittwieser, I. Antonoglou, M. Lai, A. Guez, and D. Hassabis · 2017
Earlier work this paper cites.
Structured analytic techniques for intelligence analysis
R. H. Pherson and R. J. Heuer · 2019
Earlier work this paper cites.
Measuring mathematical problem solving with the math dataset, 2021
Original
D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, and J. Steinhardt · 2021
Earlier work this paper cites.
Show your work: Scratchpads for intermediate computation with language models, 2021
Original
M. Nye, A. J. Andreassen, G. Gur-Ari, H. Michalewski, J. Austin, D. Bieber, and A. Odena · 2021
Earlier work this paper cites.
Autocast++: Enhancing world event prediction with zero-shot ranking-based context retrieval, 2023
Original
Q. Yan, R. Seraj, J. He, L. Meng, and T. Sylvain · 2023
Earlier work this paper cites.
Gpqa: A graduate-level google-proof q&a benchmark, 2023
Original
D. Rein, B. L. Hou, A. C. Stickland, J. Petty, R. Y. Pang, J. Dirani, and S. R. Bowman · 2023
Earlier work this paper cites.
Nash learning from human feedback, 2023
Original
R. Munos, M. Valko, D. Calandriello, M. G. Azar, M. Rowland, Z. D. Guo, Y. Tang, M. Geist, T. Mesnard, C. Fiegel, A. Michi, M. Selvi, S. Girgin, N. Momchev, O. Bachem, D. J. Mankowitz, D. Precup, and B. Piot · 2023
Earlier work this paper cites.

Similar

Expertprompting: Instructing large language models to be distinguished experts, 2023
Original
B. Xu, A. Yang, J. Lin, Q. Wang, C. Zhou, Y. Zhang, and Z. Mao · 2023
Cited alongside, same era.
Forecastbench: A dynamic benchmark of ai forecasting capabilities, 2024
Original
E. Karger, H. Bastani, C. Yueh-Han, Z. Jacobs, D. Halawi, F. Zhang, and P. E. Tetlock · 2024
Cited alongside, same era.
Financial statement analysis with large language models, 2024
Original
A. Kim, M. Muhn, and V. Nikolaev · 2024
Cited alongside, same era.
From news to forecast: Integrating event analysis in llm-based time series forecasting with reflection, 2024
Original
X. Wang, M. Feng, J. Qiu, J. Gu, and J. Zhao · 2024
Cited alongside, same era.

Then

Direct preference optimization: Your language model is secretly a reward model
R. Rafailov, A. Sharma, E. Mitchell, C. D. Manning, S. Ermon, and C. Finn · 2024
Later among the works it cites.
Is dpo superior to ppo for llm alignment? a comprehensive study, 2024
Original
S. Xu, W. Fu, J. Gao, W. Ye, W. Liu, Z. Mei, and Y. Wu · 2024
Later among the works it cites.
Phi-4 technical report, 2024
Original
M. Abdin, J. Aneja, H. Behl, S. Bubeck, R. Eldan, S. Gunasekar, and Y. Zhang · 2024
Later among the works it cites.
Gpt-4o system card, 2024
Original
A. Hurst, A. Lerer, A. P. Goucher, A. Perelman, A. Ramesh, A. Clark, and I. Kivlichan · 2024
Later among the works it cites.
Qwen2.5 technical report, 2024
Original