4 papers
Predictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models
Katrina Brown, Aneesh Muppidi, Rana Shahout
Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per q…
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…
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…
Diverse Concept Proposals for Concept Bottleneck Models
Katrina Brown, Marton Havasi, Finale Doshi-Velez
Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number o…