CoChat

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Open access
Usman Anwar, Abulhair Saparov, Javier Rando Ramírez, Daniel Paleka, Miles Turpin, Hase, Peter, Ekdeep Singh Lubana, Erik Jenner, Casper, Stephen, Oliver Sourbut, Edelman, Benjamin L., Zhang, Zhaowei, Günther, Mario, Anton Korinek, Hernandez-Orallo, Jose, Hammond, Lewis, Bigelow, Eric, Pan, Alexander, Lauro Langosco, Tomasz Korbak, Zhang, Heidi Chenyu, Ruiqi Zhong, Seán S. ÓhÉigeartaigh, Gabriel L. Recchia, Corsi, Giulio, Alan Chan, Markus Anderljung, Edwards, Lilian, Aleksandar Petrov, Christian A. Schroeder de Witt, Sumeet Motwani, Yoshua Bengio, Danqi Chen, Torr, Philip H.S., Samuel Albanie, Tegan Maharaj, Jakob N. Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Choi, Yejin, David Krueger · 2024 · arXiv (Cornell University)
PreprintCited by 17

The DOI matches its OpenAlex record; 141 of the 141 references it cites were found in a registry or an index.

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

OpenAlex · 10.3929/ethz-b-000706962

Cites

141 of 141 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

Show all 141 references

Cited by

See all 17

Metadata

Authors
Anwar, U., Saparov, A., Ramírez, J. R., Paleka, D., Turpin, M., Hase, P., Lubana, E. S., Jenner, E., Casper, S., Sourbut, O., Edelman, B. L., Zhang, Z., Günther, M., Korinek, A., Hernandez-Orallo, J., Hammond, L., Bigelow, E., Pan, A., Langosco, L., Korbak, T., Zhang, H. C., Zhong, R., ÓhÉigeartaigh, S. S., Recchia, G. L., Corsi, G., Chan, A., Anderljung, M., Edwards, L., Petrov, A., de Witt, C. A. S., Motwani, S., Bengio, Y., Chen, D., Torr, P. H. S., Albanie, S., Maharaj, T., Foerster, J. N., Tramèr, F., He, H., Kasirzadeh, A., Choi, Y., & Krueger, D.
Venue
arXiv (Cornell University)
Publisher
Cornell University
Published
2024-01-01
ISSN
2331-8422 (ISSN-L)
OpenAlex
W6947695150
Cited by
17
References
141
Type
posted content
Language
en
Open access
green

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: Foundational Challenges in Assuring Alignment and Safety of Large Language Models. https://app.cochat.ai/papers/10.3929/ethz-b-000706962
The paper
Anwar, U., Saparov, A., Ramírez, J. R., Paleka, D., Turpin, M., Hase, P., Lubana, E. S., Jenner, E., Casper, S., Sourbut, O., Edelman, B. L., Zhang, Z., Günther, M., Korinek, A., Hernandez-Orallo, J., Hammond, L., Bigelow, E., Pan, A., Langosco, L., . . . Krueger, D. (2024). Foundational Challenges in Assuring Alignment and Safety of Large Language Models. arXiv (Cornell University). https://doi.org/10.3929/ethz-b-000706962

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.