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

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy

Open access
Imaezue, Gerald C., Maram, Krishna V., Ajayi, David, Alohali, Isra, Butta, Rajesh K. · 2026 · Journal of Speech, Language, and Hearing Research

Abstract

Purpose: Large language model (LLM)–driven conversational agents are increasingly considered for use in clinical contexts, yet systematic approaches for evaluating their behavior in impairment-rich, speech-based therapeutic interactions remain limited. This study extends the Agent-Based Conversational Dialogue (ABCD) simulation method as a preclinical testbed to evaluate how LLMs generate accessible clinician language when responding to characteristic aphasic speech during Response Elaboration Training. Method: ABCD was used to simulate multi-turn spoken therapeutic dialogues between an LLM-driven clinician and an artificial intelligence (AI)–simulated aphasic patient, enabling controlled manipulation of impairment profiles, prompting strategies, and reasoning modes without human participants. Three LLM families (Claude, GPT, and Gemini) were benchmarked under zero-shot and few-shot prompting and standard versus advanced reasoning. Response accessibility was quantified using established readability metrics (Flesch Reading Ease, Dale–Chall) and a composite score derived from 16 standardized readability measures. Results: Distinct accessibility signatures emerged across model architectures and configurations. Few-shot prompting and advanced reasoning generally yielded more accessible clinician responses, whereas Gemini demonstrated superior accessibility under zero-shot, standard reasoning. Conclusions: LLMs differ systematically in their capacity to adapt clinician language to impaired speech. ABCD provides a scalable, preclinical dialogue simulation framework for benchmarking conversational AI in clinically oriented, impairment-rich dialogue across multidimensional constraints. It offers guidance for model selection and configuration prior to clinical translation in communication rehabilitation. Supplemental Material: https://doi.org/10.23641/asha.32736078

Overview

Integrity signals

Registry

Crossref · 10.1044/2026_jslhr-26-00031

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 40 references

Research works printed but not linked: 5

  1. Broca, P. (1861). Remarks on the seat of the faculty of articulated language, following an observation of aphemia (loss of speech). Bulletin de la Société Anatomique, 6, 330–357.
  2. Brunato, D. (2025). Learning from impairment: Leveraging insights from clinical linguistics in language modelling research. In O. Rambow, L. Wanner, M. Apidianaki, H. Al-Khalifa, B. D. Eugenio, & S. Schockaert (Eds.), Proceedings of the 31st International Conference on Computational Linguistics (pp. 4167–4174). Association for Computational Linguistics. https://aclanthology.org/2025.coling-main.281/
  3. Dale, E., & Chall, J. S. (1948). A formula for predicting readability. Educational Research Bulletin, 27(1), 11–28. https://www.jstor.org/stable/1473169
  4. Wang X. Wei J. Schuurmans D. Le Q. Chi E. H. Narang S. Chowdhery A. & Zhou D. (2023). Self-consistency improves chain of thought reasoning in language models. In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023). https://openreview.net/forum?id=1PL1NIMMrw
  5. Zheng L. Chiang W.-L. Sheng Y. Zhuang S. Wu Z. Zhuang Y. Lin Z. Li Z. Li D. Xing E. P. Zhang H. Gonzalez J. E. & Stoica I. (2023). Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. Advances in Neural Information Processing Systems 36. https://papers.nips.cc/paper_files/paper/2023/hash/91f18a1287b398d378ef22505bf41832-Abstract-Datasets_and_Benchmarks.html

Cited by

See all 1

Metadata

Authors
Imaezue, G. C., Maram, K. V., Ajayi, D., Alohali, I., & Butta, R. K.
Affiliations
University of South Florida (US)
Venue
Journal of Speech, Language, and Hearing Research
Published
2026-08-11
Volume
69
Issue
8
Pages
3781-3796
ISSN
  • 1092-4388 (ISSN-L)
  • 1558-9102
OpenAlex
W7165759985
Cited by
1
References
40
Citations by year
2026: 1
FWCI
3.37
Type
journal article
Language
en
Open access
Licence
cc-by-nc-sa
Locations
  • Journal of Speech Language and Hearing Research (publishedVersion, cc-by-nc-sa)
  • PubMed (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
Keywords
aphasia rehabilitation, large language models, chatbots, dialogue simulation, readability, few-shot prompting, zero-shot prompting, modes of reasoning, communication rehabilitation, preclinical evaluation, LLM benchmarking
MeSH terms
Large Language Models, Generative Artificial Intelligence, Aphasia, Artificial Intelligence, Communication, Computer Simulation, Humans, Language Therapy

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: Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy. https://app.cochat.ai/papers/10.1044/2026_jslhr-26-00031
The paper
Imaezue, G. C., Maram, K. V., Ajayi, D., Alohali, I., & Butta, R. K. (2026). Preclinical Dialogue Simulation: Evaluating Response Accessibility in Conversational Artificial Intelligence for Aphasia Therapy. Journal of Speech, Language, and Hearing Research. https://doi.org/10.1044/2026_jslhr-26-00031

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.