3 papers
cs.AI2026
JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory
Louie Hong Yao, Nicholas Jarvis, Tiffany Zhan +3
Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature. We present JE-IRT, a geometric item-response fr…
cs.CL2026
Cross-Lingual Steering for Figurative Language Generation
Linfeng Liu, Tiffany Zhan, Louie Hong Yao +2
Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reusable across languages is un…
cs.CL2026
Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
Daniel Vennemeyer, Phan Anh Duong, Tiffany Zhan +1
Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from…