stat.ME · 2026-11-14 · No. 171

Methodology, 2026-11-14.

1 new papers in stat.ME. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

1 entries
  1. 01

    When Both Sides Adapt: The Challenges of Evaluating Interactive LLM Systems

    Hannah Li

    stat.ME · cs.AI

    In interactive systems where users engage with LLMs, users are adaptive and, after observing LLM responses, can change their prompting strategy, as well as the type and difficulty of subsequent tasks. Thus model responses can influence the set of prompts on which the model is subsequently evaluated. We study the implications of this user adaptivity and prompt endogeneity for the evaluation of LLMs. We define two classes of estimands for...

    arxiv.org/abs/2611.17239 · PDF

This edition is part of The Daily Abstract — stat.ME archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.