Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1446
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-15T10:43:22.124482Z
status: published
lens: trace
sector: health
headline: A Conversational Agent for Providing Personalized Preexposure Prophylaxis (PrEP) Support: Protocol for Chatbot Implementation and Evaluation
dek: Background Chatbots have the potential to reduce barriers to preexposure prophylaxis (PrEP), including lack of awareness, misconceptions, and stigma, by providing anonymous and continuous support. However, in the context of PrEP, chatbots are still nascent; they lack personalized informational expertise, peer experiential expertise, and human-like emotional support to facilitate future PrEP uptake. These personalized and relatable forms of support are crucial for increasing engagement, influencing health decisio…
gain_title: In a blinded comparison, a retrieval-augmented PrEP chatbot was preferred over real-world user responses and matched or beat a general LLM on empathy and tone.
problem_title: The specialized RAG chatbot was rated below a general LLM on most evaluation criteria, so its added value for PrEP support remains unproven.
trace_subject: RAG chatbot for personalized PrEP support
gain_reading: In a blinded comparison, a retrieval-augmented PrEP chatbot was preferred over real-world user responses and matched or beat a general LLM on empathy and tone.
gain_evidence: both the general LLM and RAG were preferred over user responses | with the exceptions of empathy and tone
problem_reading: The specialized RAG chatbot was rated below a general LLM on most evaluation criteria, so its added value for PrEP support remains unproven.
problem_evidence: the general LLM maintained a superior edge over the RAG chatbot across most criteria
quick_read: Researchers built a chatbot for people considering preexposure prophylaxis. It splits incoming queries, classifies whether they ask for information, emotional support, or context, and retrieves relevant social media documents before the Gemini-2.0-flash model writes a reply. After ten internal evaluation rounds, they ran a blinded comparison against a general LLM and real-world user responses.

The work matters because PrEP uptake is held back by lack of awareness, misconceptions, and stigma, and an anonymous, always-available tool could help. Yet the specialized chatbot did not beat a general LLM on most criteria, and expert and user feedback has not yet been gathered, so its real-world benefit is still uncertain.
limitation: The chatbot's potential is not yet validated: expert and user feedback is still to come, and the general LLM outperformed it on most criteria.
tag: Dual reading
key_points: The system pairs a query preprocessor using Segment Any Text and a fine-tuned Gemma 2 support classifier with a retrieval-augmented generation module. | Retrieval relied on SBERT embeddings with cosine similarity plus topic matching to select relevant documents. | Internal rounds scored responses on 10 criteria, including accuracy, actionability, tone, and empathy. | Prompt decomposition and segmenting instructions improved comprehensiveness and relevancy for complex, long queries. | Prompt effectiveness varied with task complexity, likely due to LLM sensitivity to prompt structure and linguistic variability.
rundown: The development followed two phases: prototype conceptualization, in which real-world PrEP needs were identified and a dialogue flow diagram designed, and iterative chatbot development. The aim was to deliver personalized information, peer experiential expertise, and human-like emotional support.

Evaluation combined ten internal rounds with a blinded comparative study analyzed by a linear mixed model. Both the general LLM and the RAG chatbot were preferred over real-world user responses, but the general LLM led on most criteria except empathy and tone.

The authors conclude the chatbot uses social media data to address PrEP misconceptions and promote self-efficacy, and say further analysis with expert and user feedback will be done to validate and improve it.
sources:
- peer_reviewed | JMIR Research Protocols | https://doi.org/10.2196/79966 | 2026-10-01
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

b174d8259228c2dec27df81a5d10f85587aa73c09c1e335d677b1fbf3148ab9e

previous

0000000000000000000000000000000000000000000000000000000000000000