The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities
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
“AI chatbots may also have the potential to scaffold users' information needs and engage in reference transactions, just as virtual reference altered the way librarians support users' questions (Lai 2023), especially as users are continually challenged to navigate vast quantities of information in pursuit of their answer.”
From AI on the Shoulders of Giants: Using Kuhlthau’s Information Search Process to Improve AI Support for Information-Seeking (2025) · cites this paper as Lai 2023
In the citing paper
“The reference interview (Lai 2023) provides a possible template for improving chatbots' information-seeking support.”
From AI on the Shoulders of Giants: Using Kuhlthau’s Information Search Process to Improve AI Support for Information-Seeking (2025) · cites this paper as Lai 2023
In the citing paper
“Chatbots did not provide links to resources in subscription databases but, rather, to web-accessible reports, sites, and articles related to the question (Lai 2023).”
From AI on the Shoulders of Giants: Using Kuhlthau’s Information Search Process to Improve AI Support for Information-Seeking (2025) · cites this paper as Lai 2023
In the citing paper
“Chatbots also struggle to search outside of data in their language models, thus making real-time information such as library hours or event registration unavailable (Lai 2023) without adding additional AI frameworks to enable the use of private, local, or unique data.”
From AI on the Shoulders of Giants: Using Kuhlthau’s Information Search Process to Improve AI Support for Information-Seeking (2025) · cites this paper as Lai 2023
In the citing paper
“Often, users feel supported and engaged by this language, as indicated by their politeness (Rapp et al. 2023), when they interact with the chatbot (Lai 2023).”
From AI on the Shoulders of Giants: Using Kuhlthau’s Information Search Process to Improve AI Support for Information-Seeking (2025) · cites this paper as Lai 2023
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
ChatGPT: five priorities for research
van Dis, E. A. M., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023) · Nature · doi:10.1038/d41586-023-00288-7 · Cited by 1,842
Artificial intelligence in academic libraries: An environmental scan
Wheatley, A., & Hervieux, S. (2019) · Information Services and Use · doi:10.3233/isu-190065 · Cited by 222
Cited by
Ravuri, B., & Mardis, M. A. (2025) · Library Trends · doi:10.1353/lib.2025.a961195 · Cited by 9
Deploying and evaluating a conversational agent using LLMs for academic library reference
Fitzgibbons, M., Berrizbeitia, F., Chalifour, J., Stouhi, Y., Charbonneau, O., & Majerczyk, A. (2026) · Reference Services Review · doi:10.1108/rsr-05-2025-0030 · Cited by 2
Barber, S. T. (2025) · Internet Reference Services Quarterly · doi:10.1080/10875301.2025.2490489 · Cited by 1
Metadata
- Authors
- Lai, K.
- Venue
- College & Research Libraries
- Publisher
- American Library Association
- Published
- 2023
- Volume
- 84
- Issue
- 6
- ISSN
- 2150-6701
- Cited by
- 23
- References
- 2
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: How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities. https://app.cochat.ai/papers/10.5860/crl.84.6.974
- The paper
- Lai, K. (2023). How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities. College & Research Libraries. https://doi.org/10.5860/crl.84.6.974
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.