From the source
Google Research introduces ConvApparel, a dataset and evaluation framework to measure and bridge the realism gap in LLM-based user simulators, using a dual-agent protocol and counterfactual validation.
ConvApparel: Measuring and bridging the realism gap in user simulators
Research paper
From the source
We introduce ConvApparel, a new human-AI conversation dataset and a comprehensive evaluation framework designed to quantify the "realism gap" in LLM-based user simulators and improve the training of robust conversational agents.
research.google