CoChat

Evaluating language models for mathematics through interactions

Open access
Collins, Katherine M., Jiang, Albert Q., Frieder, Simon, Wong, Lionel, Zilka, Miri, Bhatt, Umang, Lukasiewicz, Thomas, Wu, Yuhuai, Tenenbaum, Joshua B., Hart, William, Gowers, Timothy, Li, Wenda, Weller, Adrian, Jamnik, Mateja · 2024 · Proceedings of the National Academy of Sciences
Cited by 49

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1073/pnas.2318124121

Cites

39 of 39 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Cited by

See all 49

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.