Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language Models
Sid Bharthulwar, John Rho, Katrina Brown
We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt upd…
cs.CL2025
Order Independence With Finetuning
Katrina Brown, Reid McIlroy
Large language models (LLMs) demonstrate remarkable performance on many NLP tasks, yet often exhibit order dependence: simply reordering semantically identical tokens (e.g., answer…
cs.CL2024
Order-Independence Without Fine Tuning
Reid McIlroy-Young, Katrina Brown, Conlan Olson +2
The development of generative language models that can create long and coherent textual outputs via autoregression has lead to a proliferation of uses and a corresponding sweep of…