hansonhl / antra
Package for defining computation graphs and performing intervention experiments
☆14Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for antra
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆85Updated 3 years ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆95Updated last year
- ☆87Updated 2 years ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆42Updated last year
- ☆33Updated 9 months ago
- This code accompanies the paper "Bayesian Framework for Information-Theoretic Probing" published in EMNLP 2021.☆11Updated 3 years ago
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆49Updated last year
- NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790☆27Updated 2 years ago
- ☆28Updated last year
- ☆42Updated 10 months ago
- ☆10Updated 2 years ago
- Codebase implementing LMs for learning the Dyck-(k,m) bounded hierarchical language☆15Updated 4 years ago
- ☆17Updated 10 months ago
- ☆86Updated last year
- ☆103Updated 2 years ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆30Updated 8 months ago
- [ACL 2020] Towards Debiasing Sentence Representations☆61Updated 2 years ago
- EMNLP 2020: On the Ability and Limitations of Transformers to Recognize Formal Languages☆24Updated 4 years ago
- Rationales for Sequential Predictions☆40Updated 2 years ago
- This code accompanies the paper "Information-Theoretic Probing for Linguistic Structure" published in ACL 2020.☆20Updated 4 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆69Updated 3 months ago
- ☆95Updated 2 years ago
- Paper: Learning to Recombine and Resample Data for Compositional Generalization☆10Updated 4 years ago
- ☆62Updated last year
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆84Updated 2 years ago
- Pytorch implementation of DiffMask☆55Updated last year
- ☆38Updated 3 years ago
- Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"☆74Updated 3 years ago
- ☆58Updated 2 years ago
- ☆34Updated 6 months ago