Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs
Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuous prompts. These methods are usually compared through downstream performance, although similar outputs need not arise from similar internal computations. We study how...
Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov et al.
· 0 citations