Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-2315
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-30T06:46:02.962668Z
status: published
lens: p_space
sector: health
headline: Quality and readability of large language model–generated responses on type 2 diabetes remission: a cross-sectional balanced factorial study
dek: Abstract Large language models (LLMs) are increasingly being explored for patient education and medical information delivery. However, their outputs may involve trade-offs among medical accuracy, comprehensiveness, empathy, and readability. Type 2 diabetes remission is a clinically nuanced concept that is readily misunderstood by patients, making it a suitable context in which to evaluate both the medical quality and patient accessibility of artificial intelligence–generated health information. To systematically…
gain_title: (none)
problem_title: Chatbot answers about type 2 diabetes remission could not be optimized on every measure at once, and the easiest-to-read answers scored lower on comprehensiveness and falsehood avoidance.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: Chatbot answers about type 2 diabetes remission could not be optimized on every measure at once, and the easiest-to-read answers scored lower on comprehensiveness and falsehood avoidance.
problem_evidence: negatively correlated with Comprehensiveness, Falsehood avoidance, and the Composite quality score
quick_read: Researchers asked four AI chatbots, DeepSeek-V3.2, GPT-5.5, Gemini 3.1 Pro and Claude Sonnet 4.6, 16 questions about type 2 diabetes remission, using six prompting styles. That produced 384 responses. Two endocrinologists rated each on accuracy, relevance, comprehensiveness, empathy and avoiding falsehoods, and readability was scored with standard formulas.

The findings matter because patients may rely on chatbots for health information, and the study shows that the choice of model and of prompt changes what they receive. Gains in readability or empathy came with losses elsewhere. The results cover one narrow question set, and the correlation analysis was exploratory, so they cannot be taken as general proof.
limitation: The correlation analysis between readability and quality did not account for clustering within question and was intended for hypothesis generation only, and findings apply only to the type 2 diabetes remission question set.
tag: Evidence-backed problem
key_points: Composite quality scores ranged from 4.175 for Gemini 3.1 Pro to 4.285 for DeepSeek-V3.2. | GPT-5.5 had the highest mean accuracy (4.448) and falsehood avoidance (4.469). | The 6th-grade prompt gave the easiest text (FRES 69.70), while the Doctor prompt gave the hardest (27.50). | Prompting strategy had its largest effect on empathy (LR χ² = 243.836). | Readability correlated positively with empathy (ρ = 0.53) but negatively with comprehensiveness (ρ = −0.46).
rundown: The study used a balanced factorial design: four models crossed with six prompting strategies (Keyword, Question, 6th-grade, Guideline, Patient and Doctor) across 16 core questions. All 384 responses were analyzed with no missing data.

Two endocrinologists with more than 5 years of experience independently rated responses on 5-point scales using a prespecified rubric. Quality ratings were analyzed with cumulative link mixed models and readability with linear mixed-effects models, with question as a random intercept.

DeepSeek-V3.2 scored highest on relevance (4.948), comprehensiveness (4.427) and empathy (3.615). Claude Sonnet 4.6 produced the hardest text on average (FRES 32.98), compared with 51.28 for DeepSeek-V3.2. The Patient prompt gave the highest empathy (4.359) and the Doctor prompt the highest comprehensiveness (4.609).
sources:
- peer_reviewed | Scientific Reports | https://doi.org/10.1038/s41598-026-75455-7 | 2026-10-29
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

61b04d8b26a4c0c1487825f03c43166164de354a722631935d17de18974b128c

previous

0000000000000000000000000000000000000000000000000000000000000000