LSLE is a two-stage framework that constructs literacy-stratified LLM personas and benchmarks their evaluation outputs against human response distributions from VLAT and BeauVIS validation studies.
LLMs’ ways of seeing User Personas, Sept
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.HC 3representative citing papers
GPT-4o identified only 21.2% of the usability issues found by human experts in heuristic evaluation, while discovering 27 additional issues and exhibiting difficulties with certain heuristics and generating false positives.
A scoping review of 81 articles finds generative AI widely applied to persona development with 61% resource sharing but 45% lacking evaluation and frequent GPT-only use, proposing guidelines to address circularity and reduced human oversight.
citing papers explorer
-
LLM-Based Visualization Evaluation: How Well Do Literacy-Stratified Personas Approximate Human Judgments?
LSLE is a two-stage framework that constructs literacy-stratified LLM personas and benchmarks their evaluation outputs against human response distributions from VLAT and BeauVIS validation studies.
-
Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
GPT-4o identified only 21.2% of the usability issues found by human experts in heuristic evaluation, while discovering 27 additional issues and exhibiting difficulties with certain heuristics and generating false positives.
-
Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles
A scoping review of 81 articles finds generative AI widely applied to persona development with 61% resource sharing but 45% lacking evaluation and frequent GPT-only use, proposing guidelines to address circularity and reduced human oversight.