183 citations · 552 across the 27 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits
Kajetan Dymkiewicz, Tim Farrelly, Adam Práda +8
Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted generalisation by requesting the und…
cs.AI2025
KidsArtBench: Multi-Dimensional Children's Art Evaluation with Attribute-Aware MLLMs
Mingrui Ye, Chanjin Zheng, Zengyi Yu +4
Multimodal Large Language Models (MLLMs) show remarkable progress across many visual-language tasks; however, their capacity to evaluate artistic expression remains limited. Aesthe…