Personalized conversational shopping requires maintaining preference consistency over multi-turn interactions, where users reveal constraints gradually. Existing approaches often rely on static profiles and do not explicitly control long-horizon interaction behavior. We propose a multi-agent, multimodal Retrieval-Augme...
Membership inference on large language models (LLMs) aims to determine whether a given text sample was included in an LLM's training data, without access to its training corpus. Despite recent progress, existing benchmarks suffer from three limitations: limited coverage of training stages, insufficient distributional a...
Tao-Quan Shi, Chao Xiang, Qiong-Kai Xu et al.· 0 citations
This work proposes an LLM-as-a-judge approach to measure perturbation strength in a unified manner across input and CoT perturbations and suggests that judgments about a model's self-consistency is fair only within the same perturbation type.
Hangman, a novel type of steering vector that operates using word senses, as well as AutoLexSteer, the first fully automated process for building steering vectors, are introduced.
Shuhe Wang, Lachlan O. Cowley, Eduard H. Hovy et al.· 0 citations
MultiGhostBench is introduced, a multilingual benchmark comprising 928 books generated by five recent LLMs across six languages and three scripts, with an average length of approximately 59K words per book, that supports evaluation under domain, author, and language shifts.
M. Greco, Anudeex Shetty, Andrea Tagarelli et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
