hansonhl / antra
Package for defining computation graphs and performing intervention experiments
☆14Updated 3 years ago
Alternatives and similar repositories for antra:
Users that are interested in antra are comparing it to the libraries listed below
- ☆11Updated 2 years ago
- ☆63Updated last year
- EMNLP 2020: On the Ability and Limitations of Transformers to Recognize Formal Languages☆25Updated 4 years ago
- ☆87Updated 2 years ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆101Updated last year
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆20Updated 4 years ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆42Updated last year
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆50Updated last year
- ☆28Updated last year
- Diagnostic benchmark suite to explicitly test logical relational reasoning on natural language☆91Updated 8 months ago
- Paper: Learning to Recombine and Resample Data for Compositional Generalization☆10Updated 4 years ago
- ☆26Updated 2 years ago
- ☆33Updated last month
- ROCK Framework for Commonsense Causality Reasoning (CCR)☆10Updated last year
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- ☆24Updated 3 years ago
- NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790☆27Updated 2 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆69Updated 5 months ago
- This code accompanies the paper "Bayesian Framework for Information-Theoretic Probing" published in EMNLP 2021.☆10Updated 3 years ago
- A library for efficient patching and automatic circuit discovery.☆48Updated 2 months ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆74Updated last year
- ☆33Updated 3 years ago
- ☆42Updated last year
- ☆18Updated 11 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆89Updated 3 years ago
- ☆10Updated 2 years ago
- Suite of 500 procedurally-generated NLP tasks to study language model adaptability☆21Updated 2 years ago
- N/A☆18Updated 2 years ago
- ☆48Updated last year
- ☆13Updated 3 years ago