Black-box language model explanation by context length probing

Abstract: The increasingly widespread adoption of LLMs has highlighted the need for improving their explainability. We present context length probing, a novel explanation technique for causal LLMs, based on tracking the predictions of a model as a function of the length of available context, and allowing to assign differential importance scores to different contexts. The technique is model-agnostic and does not rely on access to model internals beyond computing token-level probabilities. We apply context length probing to large pre-trained LLMs and offer some initial analyses and insights, including the potential for studying long-range dependencies. The source code and an interactive demo of the method are available.