3 papers
cs.LG2025
Disentangling Representations through Multi-task Learning
Pantelis Vafidis, Aman Bhargava, Antonio Rangel
Intelligent perception and interaction with the world hinges on internal representations that capture its underlying structure (''disentangled'' or ''abstract'' representations). D…
cs.CL2024
Prompt Baking
Aman Bhargava, Cameron Witkowski, Alexander Detkov +1
Two primary ways to change LLM behavior are prompting and weight updates (e.g., fine-tuning). Prompting LLMs is simple and effective, specifying the desired changes explicitly in n…
cs.CL2024
What's the Magic Word? A Control Theory of LLM Prompting
Aman Bhargava, Cameron Witkowski, Shi-Zhuo Looi +1
Prompt engineering is crucial for deploying LLMs but is poorly understood mathematically. We formalize LLM systems as a class of discrete stochastic dynamical systems to explore pr…