Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Deploying and evaluating a conversational agent using LLMs for academic library reference

Abstract

This study has two aims. First, we sought to implement a RAG-based GenAI system capable of answering reference questions. Second, we aimed to develop an evaluation protocol to assess the chatbot by means of comparing implementations that use three different LLMs. An evaluation rubric was piloted to gauge its viability as an assessment tool. The RAG-based chatbot uses a two-step approach. First, in response to a query, the system retrieves relevant documents from a knowledge base. Each document is vectorized and matched by relevance. Second, retrieved data is combined with an LLM's generative capabilities to produce a context-aware response. Fourteen common questions representing different areas of the knowledge base were tested with the chatbot versions. The research team developed and then used an evaluation rubric to score the chatbots' responses according to: accuracy, groundedness, elicitation, completeness and further assistance. The rubric was also evaluated by calculating the standard deviation among reviewers' scores. The RAG implementations were largely successful in restricting the chatbot's responses to the knowledge base. The evaluation rubric was effective for assessing the models, highlighting each's strengths and weaknesses. Despite the evaluation being subjective, the evaluators gave similar scores, with the greatest variation in the elicitation dimension. This study offers a technical description of a practical way to implement a RAG-based chatbot in a librar…

Overview

Integrity signals

Registry

Crossref · 10.1108/rsr-05-2025-0030

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 18 references

Research works printed but not linked: 3

  1. Bryant, 2024, Implementing an AI reference chatbot at the university of Calgary library, Hanging Together
  2. University of Oklahoma Libraries, .., Project Highlight: Bizzy Chat Bot | OU Libraries
  3. University of Texas Libraries, 2024, Building a bot: an exploration of AI to assist librarians, TexLibris

Metadata

Authors
Fitzgibbons, M., Berrizbeitia, F., Chalifour, J., Stouhi, Y., Charbonneau, O., & Majerczyk, A.
Affiliations
Concordia University (CA)
Venue
Reference Services Review
Publisher
Emerald
Published
2026-01-22
Volume
54
Issue
1
Pages
66-79
ISSN
  • 0090-7324 (ISSN-L)
  • 2054-1716
OpenAlex
W7125387752
Cited by
2
References
18
Citations by year
2026: 2
FWCI
9.42
Type
journal article
Language
en
Open access
closed
Locations
Reference Services Review (publishedVersion)
Funders
  • Concordia University Applied AI Institute (Collaborations with Industry Program)
  • Concordia University Library (Library Research Grant)
Topics
  • Social Sciences › Library and Information Sciences › Web and Library Services
  • Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
  • Social Sciences › Library and Information Sciences › Library Science and Information
Keywords
chatbots, large language models, reference questions, academic libraries, retrieval-augmented generation, chatbot evaluation, assessment rubrics, knowledge base retrieval, vector matching, LLM comparison

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: Deploying and evaluating a conversational agent using LLMs for academic library reference. https://app.cochat.ai/papers/10.1108/rsr-05-2025-0030
The paper
Fitzgibbons, M., Berrizbeitia, F., Chalifour, J., Stouhi, Y., Charbonneau, O., & Majerczyk, A. (2026). Deploying and evaluating a conversational agent using LLMs for academic library reference. Reference Services Review. https://doi.org/10.1108/rsr-05-2025-0030

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.