mohsenfayyaz / DecompXLinks
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]
☆18Updated last year
Alternatives and similar repositories for DecompX
Users that are interested in DecompX are comparing it to the libraries listed below
Sorting:
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21Updated 2 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆29Updated 2 years ago
- ☆85Updated last year
- The geometry of multilingual language model representations (EMNLP 2022).☆21Updated 2 years ago
- Easy-to-use framework for evaluating cross-lingual consistency of factual knowledge (Supported LLaMA, BLOOM, mT5, RoBERTa, etc.) Paper he…☆23Updated 2 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆54Updated last year
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆24Updated 2 months ago
- An original implementation of the paper "CREPE: Open-Domain Question Answering with False Presuppositions"