epfl-dlab / invariant-language-models
A framework to train language models to learn invariant representations.
☆12Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for invariant-language-models
- Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"☆13Updated 2 years ago
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆37Updated 11 months ago
- The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (NeurIPS 2022)☆14Updated last year
- ☆10Updated 3 years ago
- ☆24Updated 3 years ago
- ☆24Updated last year
- Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"☆17Updated 3 years ago
- ☆33Updated 3 years ago
- ☆42Updated 10 months ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Updated last year
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆20Updated 2 years ago
- Restore safety in fine-tuned language models through task arithmetic☆26Updated 7 months ago
- ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation☆22Updated 2 years ago
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆20Updated 4 years ago
- NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790☆27Updated 2 years ago
- WikiWhy is a new benchmark for evaluating LLMs' ability to explain between cause-effect relationships. It is a QA dataset containing 9000…☆46Updated 11 months ago
- Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models☆41Updated 2 years ago
- [EMNLP 2023] Once Upon a *Time* in *Graph*: Relative-Time Pretraining for Complex Temporal Reasoning☆18Updated last year
- ☆36Updated 7 months ago
- ☆14Updated 2 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆31Updated last year
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆42Updated last year
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆40Updated 11 months ago
- A unified approach to explain conditional text generation models. Pytorch. The code of paper "Local Explanation of Dialogue Response Gene…☆18Updated 2 years ago
- [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning☆11Updated 2 years ago
- Findings of ACL'2023: Optimizing Test-Time Query Representations for Dense Retrieval☆29Updated last year
- ☆21Updated 3 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆38Updated 2 years ago
- Implementation for Variational Information Bottleneck for Effective Low-resource Fine-tuning, ICLR 2021☆38Updated 3 years ago