Approaching Human-Level Forecasting with Language Models
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Forecasting future events is important for policy and decision making. In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters. Towards this goal, we develop a retrieval-augmented LM system designed to automatically search for relevant information, generate forecasts, and aggregate predictions. To facilitate our study, we collect a large dataset of questions from competitive forecasting platforms. Under a test set published after the knowledge cut-offs of our LMs, we evaluate the end-to-end performance of our system against the aggregates of human forecasts. On average, the system nears the crowd aggregate of competitive forecasters, and in some settings surpasses it. Our work suggests that using LMs to forecast the future could provide accurate predictions at scale and help to inform institutional decision making.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Halawi et al. (2024) showcased how integrating news content can significantly improve the accuracy of predictions in real-time scenarios.”
From Is Your LLM Outdated? A Deep Look at Temporal Generalization (2025) · cites this paper as Halawi et al. (2024)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Strictly Proper Scoring Rules, Prediction, and Estimation
Gneiting, T., & Raftery, A. E. (2007) · Journal of the American Statistical Association · doi:10.1198/016214506000001437 · Cited by 5,793
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
Unsolved Problems in ML Safety
Hendrycks, D., Carlini, N., Schulman, J., & Steinhardt, J. (2021) · arXiv · doi:10.48550/arxiv.2109.13916 · Cited by 95
Self-citationUniversal Self-Consistency for Large Language Model Generation
Chen, X., Aksitov, R., Alon, U., Ren, J., Xiao, K., Yin, P., Prakash, S., Sutton, C., Wang, X., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2311.17311 · Cited by 13
Cited by
Is Your LLM Outdated? A Deep Look at Temporal Generalization
Zhu, C., Chen, N., Gao, Y., Zhang, Y., Tiwari, P., & Wang, B. (2025) · Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2025.naacl-long.381 · Cited by 33
Lookahead Bias in Pretrained Language Models
Sarkar, S., & Vafa, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4754678 · Cited by 23
Metadata
- Authors
- Halawi, D., Zhang, F., Yueh-Han, C., & Steinhardt, J.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 50426-50468
- Cited by
- 24
- References
- 5
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Approaching Human-Level Forecasting with Language Models. https://app.cochat.ai/papers/10.52202/079017-1598
- The paper
- Halawi, D., Zhang, F., Yueh-Han, C., & Steinhardt, J. (2024). Approaching Human-Level Forecasting with Language Models. Advances in Neural Information Processing Systems 37. https://doi.org/10.52202/079017-1598
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.