6 papers
How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping Structure
Zainab Afolabi, Vadim Selyutin, Zhao Gao +2
Physical understanding is crucial for decision making, yet vision models struggle to infer properties such as damping that govern how materials behave. Audio encodes such propertie…
Evolving LLM-Generated Features for Interpretable Classification
Jack Butler, Zainab Afolabi, Nikita Kozodoi
Large language models (LLMs) are increasingly used as classifiers, yet they operate as opaque systems whose decisions are difficult to interpret, which complicates their use in reg…
Test-Time Augmentation for LLMs: Where to Inject Diversity at Inference Time
Nikita Kozodoi, Zainab Afolabi, Jack Butler
Aggregating several LLM responses to the same question can improve accuracy, but every method that does so must decide where the responses should differ. Established test-time scal…
Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs
Nikita Kozodoi, Zainab Afolabi, Jack Butler
Multi-task model merging combines separately trained expert models into a single model that handles all tasks without co-training. Standard practice merges experts at their optimal…
Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
Halimat Afolabi, Zainab Afolabi, Elizabeth Friel +13
Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to…
Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection
Jack Butler, Nikita Kozodoi, Zainab Afolabi +2
As Large Language Models (LLMs) continue to evolve, practitioners face increasing options for enhancing inference-time performance without model retraining, including budget tuning…