Evaluating language models for mathematics through interactions
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants. However, the standard methodology of evaluating LLMs relies on static pairs of inputs and outputs; this is insufficient for making an informed decision about which LLMs are best to use in an interactive setting, and how that varies by setting. Static assessment therefore limits how we understand language model capabilities. We introduce CheckMate, an adaptable prototype platform for humans to interact with and evaluate LLMs. We conduct a study with CheckMate to evaluate three language models (InstructGPT, ChatGPT, and GPT-4) as assistants in proving undergraduate-level mathematics, with a mixed cohort of participants from undergraduate students to professors of mathematics. We release the resulting interaction and rating dataset, MathConverse. By analyzing MathConverse, we derive a taxonomy of human query behaviors and uncover that despite a generally positive correlation, there are notable instances of divergence between correctness and perceived helpfulness in LLM generations, among other findings. Further, we garner a more granular understanding of GPT-4 mathematical problem-solving through a series of case studies, contributed by experienced mathematicians. We conclude with actionable takeaways for ML practitioners and mathematicians: models that communicate uncertainty, respond well to user corrections, and can provide a concise rationale for their recommendations, may constitute better assistants. Humans should inspect LLM output carefully given their current shortcomings and potential for surprising fallibility.
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.
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Self-citationAyers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158
Explainable machine learning in deployment
Bhatt, U., Xiang, A., Sharma, S., Weller, A., Taly, A., Jia, Y., Ghosh, J., Puri, R., Moura, J. M. F., & Eckersley, P. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3375624 · Cited by 633
Self-citationTraining Verifiers to Solve Math Word Problems
Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.14168 · Cited by 575
Mathematical Capabilities of ChatGPT
Frieder, S., Pinchetti, L., Chevalier, A., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P. C., & Berner, J. (2023) · arXiv · doi:10.48550/arxiv.2301.13867 · Cited by 385
Self-citation(2022) · doi:10.52202/068431-0278 · Cited by 358
Self-citationLee, M., Liang, P., & Yang, Q. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502030 · Cited by 345
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Bhatt, U., Antorán, J., Zhang, Y., Liao, Q. V., Sattigeri, P., Fogliato, R., Melançon, G., Krishnan, R., Stanley, J., Tickoo, O., et al. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462571 · Cited by 300
Self-citationKocielnik, R., Amershi, S., & Bennett, P. N. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300641 · Cited by 277
Risk and Uncertainty Communication
Spiegelhalter, D. (2017) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-010814-020148 · Cited by 248
Mirowski, P., Mathewson, K. W., Pittman, J., & Evans, R. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581225 · Cited by 240
Automation bias in intelligent time critical decision support systems
Cummings, M. L. (2017) · Decision Making in Aviation · doi:10.4324/9781315095080-17 · Cited by 233
Locating and Editing Factual Associations in GPT
Meng, K., Bau, D., Andonian, A., & Belinkov, Y. (2022) · arXiv · doi:10.48550/arxiv.2202.05262 · Cited by 230
In Pursuit of Error: A Survey of Uncertainty Visualization Evaluation
Hullman, J., Qiao, X., Correll, M., Kale, A., & Kay, M. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2864889 · Cited by 187
Miller, T. (2023) · 2023 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3593013.3594001 · Cited by 172
Acquisition of chess knowledge in AlphaZero
McGrath, T., Kapishnikov, A., Tomašev, N., Pearce, A., Wattenberg, M., Hassabis, D., Kim, B., Paquet, U., & Kramnik, V. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2206625119 · Cited by 166
Wilder, B., Horvitz, E., & Kamar, E. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/212 · Cited by 118
Communicating crisis uncertainty: A review of the knowledge gaps
Liu, B. F., Bartz, L., & Duke, N. (2016) · Public Relations Review · doi:10.1016/j.pubrev.2016.03.003 · Cited by 115
History of Interactive Theorem Proving
Harrison, J., Urban, J., & Wiedijk, F. (2014) · Handbook of the History of Logic · doi:10.1016/b978-0-444-51624-4.50004-6 · Cited by 107
Rethink reporting of evaluation results in AI
Burnell, R., Schellaert, W., Burden, J., Ullman, T. D., Martinez-Plumed, F., Tenenbaum, J. B., Rutar, D., Cheke, L. G., Sohl-Dickstein, J., Mitchell, M., et al. (2023) · Science · doi:10.1126/science.adf6369 · Cited by 104
Self-citationBaldur: Whole-Proof Generation and Repair with Large Language Models
First, E., Rabe, M. N., Ringer, T., & Brun, Y. (2023) · Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3611643.3616243 · Cited by 94
Evaluating Human-Language Model Interaction
Lee, M., Srivastava, M., Hardy, A., Thickstun, J., Durmus, E., Paranjape, A., Gerard-Ursin, I., Li, X. L., Ladhak, F., Rong, F., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.09746 · Cited by 61
Memory-Based Model Editing at Scale
Mitchell, E., Lin, C., Bosselut, A., Manning, C. D., & Finn, C. (2022) · arXiv · doi:10.48550/arxiv.2206.06520 · Cited by 51
Wong, L., Grand, G., Lew, A. K., Goodman, N. D., Mansinghka, V. K., Andreas, J., & Tenenbaum, J. B. (2023) · arXiv · doi:10.48550/arxiv.2306.12672 · Cited by 36
Self-citationMiniF2F: a cross-system benchmark for formal Olympiad-level mathematics
Zheng, K., Han, J. M., & Polu, S. (2021) · arXiv · doi:10.48550/arxiv.2109.00110 · Cited by 26
Formal Mathematics Statement Curriculum Learning
Polu, S., Han, J. M., Zheng, K., Baksys, M., Babuschkin, I., & Sutskever, I. (2022) · arXiv · doi:10.48550/arxiv.2202.01344 · Cited by 26
Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions
Vasconcelos, H., Bansal, G., Fourney, A., Liao, Q. V., & Vaughan, J. W. (2023) · arXiv · doi:10.48550/arxiv.2302.07248 · Cited by 23
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Jiang, A. Q., Li, W., Tworkowski, S., Czechowski, K., Odrzygóźdź, T., Miłoś, P., Wu, Y., & Jamnik, M. (2022) · arXiv · doi:10.48550/arxiv.2205.10893 · Cited by 23
Self-citationParsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
Zelikman, E., Huang, Q., Poesia, G., Goodman, N., & Haber, N. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1367 · Cited by 15
Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions
Zelikman, E., Huang, Q., Poesia, G., Goodman, N. D., & Haber, N. (2022) · arXiv · doi:10.48550/arxiv.2212.10561 · Cited by 15
Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
Wu, Z., Geiger, A., Icard, T., Potts, C., & Goodman, N. D. (2023) · arXiv · doi:10.48550/arxiv.2305.08809 · Cited by 14
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Akyürek, A. F., Akyürek, E., Madaan, A., Kalyan, A., Clark, P., Wijaya, D., & Tandon, N. (2023) · arXiv · doi:10.48550/arxiv.2305.08844 · Cited by 4
Cited by
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254
Self-citationA Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2023) · arXiv · doi:10.48550/arxiv.2307.06435 · Cited by 1,259
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
Does ChatGPT enhance student learning? A systematic review and meta-analysis of experimental studies
Deng, R., Jiang, M., Yu, X., Lu, Y., & Liu, S. (2025) · Computers & Education · doi:10.1016/j.compedu.2024.105224 · Cited by 531
Kim, S. S. Y., Vaughan, J. W., Liao, Q. V., Lombrozo, T., & Russakovsky, O. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714020 · Cited by 58
“For example, when asked a math question, an LLM may provide a step-by-step derivation for its answer [25, 44].”
Metadata
- Authors
- Collins, K. M., Jiang, A. Q., Frieder, S., Wong, L., Zilka, M., Bhatt, U., Lukasiewicz, T., Wu, Y., Tenenbaum, J. B., Hart, W., Gowers, T., Li, W., Weller, A., & Jamnik, M.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2024-06-03
- Volume
- 121
- Issue
- 24
- Pages
- e2318124121-e2318124121
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W4399281666
- Cited by
- 49
- References
- 39
- FWCI
- 18.37
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.