Repositories list

• ClimateMemes

  Public
  Python

  •0•0•0•0•Updated Sep 16, 2025Sep 16, 2025

• LiTEx

  Public
  Dataset and Implementation of the paper "LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference"

  Jupyter Notebook

  •

  Apache License 2.0

  •0•0•0•0•Updated Sep 8, 2025Sep 8, 2025

• mainlp.github.io

  Public
  MaiNLP research lab

  JavaScript

  •

  MIT License

  •1•4•0•0•Updated Sep 5, 2025Sep 5, 2025

• circuit-compositions

  Public
  This project studies the modularity of neural networks by analyzing circuits for highly compositional subtasks.

  Python

  •

  Creative Commons Attribution Share Alike 4.0 International

  •0•0•0•0•Updated Sep 4, 2025Sep 4, 2025

• common-voice

  Public
  Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

  TypeScript

  •

  Mozilla Public License 2.0

  •860•0•0•0•Updated Aug 28, 2025Aug 28, 2025

• spotlight

  Public
  Repository for the Spotlight approach and ACL'25 paper to support users in identifying the effects of LLM prompt and model changes.

  researchpatternsacl+ 2premisellm

  Python

  •0•0•0•0•Updated Jul 26, 2025Jul 26, 2025

• llm-psychometrics

  Public
  Code and data for the paper "Do LLMs Give Psychometrically Plausible Responses in Educational Assessments?" (BEA 2025)

  TeX

  •0•1•0•0•Updated Jul 25, 2025Jul 25, 2025

• MJD-Estimator

  Public
  Implementation of the EMNLP 2024 paper - "Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?; and the ACL 2025 paper - A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI

  Python

  •

  Apache License 2.0

  •0•1•0•0•Updated Jul 23, 2025Jul 23, 2025

• discourse_probes

  Public
  Implementation of experiments in "Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set".

  multilingualdiscourseinterpretability+ 3probingllmsdiscourselabels

  Python

  •

  MIT License

  •0•0•0•0•Updated Jul 9, 2025Jul 9, 2025

• xsid

  Public
  NewLisp

  •

  Creative Commons Attribution Share Alike 4.0 International

  •0•4•1•0•Updated Jul 8, 2025Jul 8, 2025

• memorized_reasonings

  Public
  Python

  •0•0•0•0•Updated Jul 2, 2025Jul 2, 2025

• semantic_components

  Public
  Finding semantic components in your neural representations.

  clusteringtext-analysisembeddings+ 1topic-modeling

  Python

  •

  MIT License

  •1•4•0•0•Updated Jun 11, 2025Jun 11, 2025

• betthupferl

  Public
  Code, (text) data, data statement + annotation guidelines for Betthupferl (“A multi-dialectal dataset for German dialect ASR and dialect-to-standard speech translation”, accepted at Interspeech 2025)

  Python

  •0•2•0•0•Updated Jun 4, 2025Jun 4, 2025

• vqa-hud

  Public
  0•0•0•0•Updated Jun 3, 2025Jun 3, 2025

• MAKIEval

  Public
  Repository for paper MAKIEval: A Multilingual Automatic WiKIdata-based Framework for Cultural Awareness Evaluation for LLMs

  Python

  •0•0•0•0•Updated May 30, 2025May 30, 2025

• CoT2EL

  Public
  Implementation of the paper "Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation"

  Apache License 2.0

  •0•0•0•0•Updated May 28, 2025May 28, 2025

• explaind

  Public
  A unified framework for attributing model components, data, and training dynamics to model behavior.

  neural-networksinterpretabilityexplainability+ 4training-dynamicsdata-attributionmodel-attributionkernel-machines

  Python

  •

  MIT License

  •0•7•0•0•Updated May 27, 2025May 27, 2025

• Multilingual-Refusal

  Public
  0•6•0•0•Updated May 22, 2025May 22, 2025

• dialetto

  Public
  Repository for the paper Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum

  Python

  •0•0•0•0•Updated May 2, 2025May 2, 2025

• SYGAR

  Public
  We extend meta-learning for compositionality to the domain of abstract spatial reasoning, demonstrating that neural networks can systematically generalize from known geometric transformations to novel combinations.

  Python

  •

  Creative Commons Attribution Share Alike 4.0 International

  •0•0•0•0•Updated Apr 17, 2025Apr 17, 2025

• False-Refusal-Mitigation

  Public
  Code for paper: [ICLR 2025] Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

  Python

  •

  Apache License 2.0

  •2•5•0•0•Updated Apr 13, 2025Apr 13, 2025

• NorSID

  Public
  Python

  •0•1•0•0•Updated Apr 2, 2025Apr 2, 2025

• karrierewege

  Public
  KARRIEREWEGE: A Large Scale Career Path Prediction Dataset

  Python

  •1•0•0•0•Updated Mar 17, 2025Mar 17, 2025

• CodeSwitchCLIR

  Public
  Python

  •

  Apache License 2.0

  •0•5•0•0•Updated Mar 12, 2025Mar 12, 2025

• auxtasks-bavarian-sid

  Public
  "Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study"

  Jupyter Notebook

  •

  MIT License

  •1•1•0•0•Updated Feb 25, 2025Feb 25, 2025

• SemEval-2024-Task-1

  Public
  Perl

  •0•0•0•0•Updated Feb 23, 2025Feb 23, 2025

• validation-gap

  Public
  A mechanistic analysis of arithmetic error detection in LLMs.

  Python

  •

  Creative Commons Attribution Share Alike 4.0 International

  •0•1•0•0•Updated Feb 18, 2025Feb 18, 2025

• JointDeBERTa

  Public
  Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"

  Python

  •

  Apache License 2.0

  •193•0•0•0•Updated Jan 17, 2025Jan 17, 2025

• WikiDIR

  Public
  Apache License 2.0

  •0•1•0•0•Updated Jan 14, 2025Jan 14, 2025

• germanic-lrl-corpora

  Public
  A survey of corpora for Germanic low-resource languages and dialects

  0•25•1•0•Updated Dec 5, 2024Dec 5, 2024