The increasingly widespread adoption of large language models has highlighted the need for improving their explainability. We present context length probing, a novel explanation technique for causal language models, 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 language models 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.
Black-box language model explanation by context length probing
Context length probing evaluates causal language models by analyzing predictions over different context lengths to assess importance scores and study long-range dependencies.
- Year
- 2022
- Venue
- arXiv 2022
- Authors
- 2
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2212.14815v3ARXIV-DEFAULT
- TL;DR
- Semantic Scholar