AIConfPaper
← Search

Yonatan Toib

2 accepted papers

2024

Improving LLM Attributions with Randomized Path-Integration

Oren Barkan, Yehonatan Elisha, Yonatan Toib, Jonathan Weill, Noam Koenigstein
EMNLP 2024finding

We present Randomized Path-Integration (RPI) - a path-integration method for explaining language models via randomization of the integration path over the attention information in the model. RPI employs integration on internal attention scores and their gradients along a randomized path, which is dy…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

LLM Explainability via Attributive Masking Learning

Oren Barkan, Yonatan Toib, Yehonatan Elisha, Jonathan Weill, Noam Koenigstein
EMNLP 2024finding

In this paper, we introduce Attributive Masking Learning (AML), a method designed for explaining language model predictions by learning input masks. AML trains an attribution model to identify influential tokens in the input for a given language model’s prediction. The central concept of AML is to t…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗