5 citations · 8 across the 4 of their papers we have counts for
4 papers · 1 filter
SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
Ethan Ludwick, Yu-Chung Hsiao
LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training. Their decisions are useful only when each judge responds reliably to changes aff…
Rethinking Verbalized Confidence for LLM-as-a-Judge: A Compatibility Shift on Post-2025 Proprietary Models
Yu-Chung Hsiao
Verbalized confidence, long dismissed as overconfident, coarse, and prone to round-number clustering, is now the more robust soft-scoring mechanism for LLM-as-a-Judge on top-tier p…
LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment
Varsha Embar, Ritvik Shrivastava, Vinay Damodaran +3
Large Language Models have transformed the Contact Center industry, manifesting in enhanced self-service tools, streamlined administrative processes, and augmented agent productivi…
ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots
Yu-Chung Hsiao, Fedir Zubach, Gilles Baechler +6
We introduce ScreenQA, a novel benchmarking dataset designed to advance screen content understanding through question answering. The existing screen datasets are focused either on…