CEBaBing / CEBaB
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
☆11Updated last year
Related projects: ⓘ
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆28Updated 6 months ago
- ☆26Updated last year
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆58Updated last year
- ☆42Updated 7 months ago
- ☆25Updated 2 years ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆39Updated last year
- Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"☆31Updated last year
- AbstainQA, ACL 2024☆17Updated 3 weeks ago
- [ACL 2020] Towards Debiasing Sentence Representations☆59Updated last year
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆37Updated 9 months ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆38Updated 9 months ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆20Updated 3 years ago
- ☆19Updated 6 months ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆83Updated 2 years ago
- ☆87Updated 2 years ago
- ☆31Updated last year
- Code repository for the paper "Mission: Impossible Language Models".☆27Updated 8 months ago
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆17Updated last year
- This code accompanies the paper "Bayesian Framework for Information-Theoretic Probing" published in EMNLP 2021.☆11Updated 3 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆11Updated last year
- ☆16Updated 2 years ago
- ☆92Updated 4 months ago
- ☆35Updated last year
- CSCW 2023 Best Demo Award: Conversational AI Explanations to Support Human-AI Scientific Writing☆12Updated last year
- Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming so…☆15Updated last year
- CausaLM: Causal Model Explanation Through Counterfactual Language Models☆54Updated 4 years ago
- tianlu-wang / Identifying-and-Mitigating-Spurious-Correlations-for-Improving-Robustness-in-NLP-ModelsNAACL 2022 Findings☆14Updated 2 years ago
- ☆13Updated 9 months ago
- ☆23Updated 2 weeks ago
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆45Updated 2 years ago