2 papers
cs.CL2026
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
cs.CL2025
Becoming Experienced Judges: Selective Test-Time Learning for Evaluators
Seungyeon Jwa, Daechul Ahn, Reokyoung Kim +2
Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployme…