allenai / contrastive-explanations

Related projects: ⓘ

• peterbhase / ExplanationRoles
  Code for paper "When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data"
  ☆14Updated 3 years ago
• peterbhase / LAS-NL-Explanations
  Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"
  ☆20Updated 3 years ago
• CoderPat / learning-scaffold
  This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"
  ☆19Updated 2 years ago
• peterbhase / ExplanationSearch
  Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"
  ☆17Updated last year
• allenai / label_rationale_association
  Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"
  ☆11Updated last year
• john-hewitt / conditional-probing
  Codebase for running (conditional) probing experiments
  ☆22Updated last year
• UVa-NLP / VMASK
  Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"
  ☆17Updated 3 years ago
• swarnaHub / ExplaGraphs
  [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning
  ☆10Updated last year
• kanekomasahiro / context-debias
  ☆25Updated 2 years ago
• yanaiela / pararel
  ☆42Updated 7 months ago
• successar / instance_attributions_NLP
  ☆17Updated 3 years ago
• hsajjad / Interpretability-Tutorial-NAACL2021
  ☆24Updated 3 years ago
• allenai / feb
  Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"
  ☆13Updated 2 years ago
• archiki / GrIPS
  Code for our paper: "GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models"
  ☆50Updated last year
• ruiqi-zhong / DescribeDistributionalDifferences
  Code for preprint: Summarizing Differences between Text Distributions with Natural Language
  ☆39Updated last year
• princeton-nlp / rationale-robustness
  NAACL 2022: Can Rationalization Improve Robustness? https://arxiv.org/abs/2204.11790
  ☆26Updated last year
• ekinakyurek / influence
  Influence Experiments
  ☆36Updated last year
• feyzaakyurek / bbnli
  Bias Benchmark for Natural Language Inference. Code repo for the Findings of NAACL 2022 paper "On Measuring Social Biases in Prompt-Based…
  ☆15Updated 2 years ago
• SawanKumar28 / nile
  NILE : Natural Language Inference with Faithful Natural Language Explanations
  ☆29Updated last year
• tapilab / aaai-2021-counterfactuals
  ☆14Updated 3 years ago
• technion-cs-nlp / bias-probing
  Debiasing Methods in Natural Language Understanding Make Bias More Accessible: Code and Data
  ☆13Updated 2 years ago
• ewsheng / decoding-biases
  Scripts to evaluate various bias metrics for different NLG models + decoding algorithms
  ☆14Updated 9 months ago
• INK-USC / ReCross
  ReCross: Unsupervised Cross-Task Generalization via Retrieval Augmentation
  ☆22Updated 2 years ago
• yuchenlin / OpenCSR
  Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
  ☆32Updated last year
• xiye17 / EvalQAExpl
  Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.
  ☆18Updated 3 years ago
• INK-USC / DIG
  Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)
  ☆24Updated 2 years ago
• gucci-j / light-transformer-emnlp2021
  EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling
  ☆31Updated 2 years ago
• nlx-group / Shortcutted-Commonsense-Reasoning
  Code for the article "Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning", Outstanding Paper at EMNLP20…
  ☆10Updated 2 years ago
• pliang279 / sent_debias
  [ACL 2020] Towards Debiasing Sentence Representations
  ☆59Updated last year
• copenlu / fever-adversarial-attacks
  Adversarial attacks against claim detection systems at FEVER
  ☆11Updated last year