mohsenfayyaz / DecompX

Related projects ⓘ

Alternatives and complementary repositories for DecompX

• mohsenfayyaz / GlobEnc
  [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
  ☆21Updated last year
• mt-upc / transformer-contributions
  Measuring the Mixing of Contextual Information in the Transformer
  ☆25Updated last year
• AmirAbaskohi / LM-CPPF
  The official implementation of the ACL 2023 paper, "Paraphrasing-Guided Data Augmentation for Contrastive Prompt-based Few-shot Fine-tuni…
  ☆10Updated 11 months ago
• nyu-mll / BBQ
  Repository for the Bias Benchmark for QA dataset.
  ☆85Updated 10 months ago
• McGill-NLP / bias-bench
  ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.
  ☆124Updated last year
• balevinstein / Probes
  ☆37Updated last year
• i-gallegos / Fair-LLM-Benchmark
  ☆109Updated last year
• tylerachang / multilingual-geometry
  The geometry of multilingual language model representations (EMNLP 2022).
  ☆15Updated 2 years ago
• Betswish / Cross-Lingual-Consistency
  Easy-to-use framework for evaluating cross-lingual consistency of factual knowledge (Supported LLaMA, BLOOM, mT5, RoBERTa, etc.) Paper he…
  ☆21Updated this week
• interpretingdl / eacl2024_transformer_interpretability_tutorial
  Materials for EACL2024 tutorial: Transformer-specific Interpretability
  ☆42Updated 7 months ago
• TideDancer / iclr21_isotropy_contxt
  ☆28Updated 3 years ago
• yasumasaonoe / entity_knowledge_propagation
  ☆16Updated last year
• dannyallover / overthinking_the_truth
  ☆26Updated 6 months ago
• launchnlp / BOLT
  Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".
  ☆18Updated last year
• beinborn / relative_importance
  ☆16Updated 2 years ago
• UKPLab / adaptable-adapters
  ☆23Updated 2 years ago
• amazon-science / bold
  Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper
  ☆65Updated 3 years ago
• yuzhaouoe / SAE-based-representation-engineering
  Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆21Updated 3 weeks ago
• allenai / unqover
  UnQovering Stereotyping Biases via Underspecified Questions - EMNLP 2020 (Findings)
  ☆19Updated 3 years ago
• myracheng / markedpersonas
  Code and data for Marked Personas (ACL 2023)
  ☆21Updated last year
• timoschick / self-debiasing
  This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".
  ☆86Updated 3 years ago
• personads / depprobe
  Probing for Labeled Dependency Trees (ACL 2022) + Sorting LMs by Structure (NAACL 2022)
  ☆8Updated 5 months ago
• mega002 / ff-layers
  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
• SLAB-NLP / BUG
  A Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation, Levy et al., Findings of EMNLP 2021
  ☆12Updated 2 years ago
• WadeYin9712 / GeoMLAMA
  ☆13Updated 2 years ago
• pliang279 / LM_bias
  [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models
  ☆60Updated 2 years ago
• gorokoba560 / norm-analysis-of-transformer
  ☆77Updated 6 months ago
• aviclu / ffn-values
  ☆58Updated last year
• guanzhchen / PETuning
  ☆32Updated last year
• psunlpgroup / MACSum
  Dataset, metrics, and models for TACL 2023 paper MACSUM: Controllable Summarization with Mixed Attributes.
  ☆34Updated last year