mt-upc / transformer-contributionsLinks
Measuring the Mixing of Contextual Information in the Transformer
☆29Updated 2 years ago
Alternatives and similar repositories for transformer-contributions
Users that are interested in transformer-contributions are comparing it to the libraries listed below
Sorting:
- The geometry of multilingual language model representations (EMNLP 2022).☆21Updated 2 years ago
- ☆19Updated last year
- ☆85Updated last year
- Materials for "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" at ICLR'24 🐑 🐑☆14Updated last year
- ☆18Updated 11 months ago
- ☆17Updated 2 years ago
- ☆34Updated 3 years ago
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆38Updated 2 years ago
- DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]☆18Updated last year
- Benchmark API for Multidomain Language Modeling☆24Updated 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
- Crosslingual Reasoning through Test-Time Scaling☆17Updated 3 weeks ago
- A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.☆73Updated 9 months ago
- ☆28Updated 6 months ago
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21Updated 2 years ago
- ☆35Updated 11 months ago
- Materials for EACL2024 tutorial: Transformer-specific Interpretability☆54Updated last year
- ☆62Updated 2 years ago
- ☆58Updated 3 years ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆41Updated last year
- Code repository for the paper "Mission: Impossible Language Models."☆52Updated last month
- Code of NAACL 2022 "Efficient Hierarchical Domain Adaptation for Pretrained Language Models" paper.☆32Updated last year
- ☆24Updated 3 years ago
- ☆16Updated 3 years ago
- ☆39Updated 3 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆24Updated 2 months ago
- ☆75Updated last year
- ☆30Updated last year
- Evaluation pipeline for the BabyLM Challenge 2023.☆75Updated last year
- ☆30Updated 4 years ago