Papers by Antoine Liutkus
Black-box language model explanation by context length probing (2023.acl-short)
Copied to clipboard
| Challenge: | *context length probing* is a new explanation technique for large language models . it tracks the predictions of a model as a function of the length of available context . |
| Approach: | They propose a method that tracks the predictions of a model as a function of the length of available context and allows to assign *differential importance scores* to different contexts. |
| Outcome: | The proposed method is model-agnostic and does not rely on access to model internals beyond token-level probabilities. |