arXiv Machine Learning By Jenny Y. Huang, Yunyi Shen, Dennis Wei, Tamara Broderick

Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings

Read the original on arXiv Machine Learning →

arXiv:2508. 11847v4 Announce Type: replace-cross Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a worst-case very small fraction of preference data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.