RecPIE jointly optimizes recommendation predictions and LLM-generated natural-language explanations via alternating training and reinforcement learning, yielding 3-4% accuracy gains and higher human preference on Google Maps POI data.
Wang et al., ``LLM4Vis: Explainable visualization recommendation using ChatGPT,'' in Proc
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A case study shows that the ATWL scaffold with an AI assistant enabled rapid creation of a visual analytics prototype testing relaxed Pareto frontiers and option constellations, yielding lessons on scaffold usage.
citing papers explorer
-
Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations
RecPIE jointly optimizes recommendation predictions and LLM-generated natural-language explanations via alternating training and reinforcement learning, yielding 3-4% accuracy gains and higher human preference on Google Maps POI data.
-
From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping
A case study shows that the ATWL scaffold with an AI assistant enabled rapid creation of a visual analytics prototype testing relaxed Pareto frontiers and option constellations, yielding lessons on scaffold usage.