Alternatives and similar repositories for parametric-faithfulness

Users that are interested in parametric-faithfulness are comparing it to the libraries listed below

• zouharvi / subset2evaluate

  View on GitHub
  Find informative examples to efficiently (human)-evaluate NLG models.
  ☆18Feb 9, 2026Updated last week
• yoavgur / PISCES

  View on GitHub
  🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models
  ☆12May 30, 2025Updated 8 months ago
• SakanaAI / TransEvalnia

  View on GitHub
  Reasoning-based Evaluation and Ranking of Translations.
  ☆19Jul 18, 2025Updated 6 months ago
• TransluceAI / introspective-interp

  View on GitHub
  Repository for "Training Language Models To Explain Their Own Computations"
  ☆20Dec 22, 2025Updated last month
• rycolab / kl-rb

  View on GitHub
  This repository contains code for the paper "Better Estimation of the KL Divergence Between Language Models"
  ☆15May 30, 2025Updated 8 months ago
• cyanic-selkie / cutters

  View on GitHub
  A rule based sentence segmentation library.
  ☆14Jul 17, 2023Updated 2 years ago
• Leukas / CUTE

  View on GitHub
  ☆19Sep 16, 2025Updated 5 months ago
• Roxot / mbr-nmt

  View on GitHub
  Sampling-Based Minimum Bayes-Risk Decoding for Neural Machine Translation
  ☆16Oct 14, 2022Updated 3 years ago
• FarnoushRJ / RelP

  View on GitHub
  [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…
  ☆27Nov 3, 2025Updated 3 months ago
• tilde-research / activault

  View on GitHub
  Engine for collecting, uploading, and downloading model activations
  ☆26Apr 2, 2025Updated 10 months ago
• hannamw / MIB-circuit-track

  View on GitHub
  ☆23Jun 30, 2025Updated 7 months ago
• visinf / fast-axiomatic-attribution

  View on GitHub
  Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)
  ☆16May 12, 2023Updated 2 years ago
• MadryLab / AT2

  View on GitHub
  Attribute statements generated by LLMs to preceding tokens using attention weights.
  ☆22Apr 22, 2025Updated 9 months ago
• yihuaihong / ConceptVectors

  View on GitHub
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆39Aug 20, 2025Updated 5 months ago
• mt-upc / transformer-contributions-nmt

  View on GitHub
  ☆18Oct 6, 2022Updated 3 years ago
• mitvis / saliency-cards

  View on GitHub
  Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!
  ☆18Jun 9, 2023Updated 2 years ago
• mohsenfayyaz / DecompX

  View on GitHub
  DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]
  ☆19Jul 3, 2025Updated 7 months ago
• xiye17 / EvalQAExpl

  View on GitHub
  Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.
  ☆18Apr 25, 2021Updated 4 years ago
• aaronmueller / MIB

  View on GitHub
  Landing page for MIB: A Mechanistic Interpretability Benchmark
  ☆24Aug 15, 2025Updated 6 months ago
• mohsenfayyaz / GlobEnc

  View on GitHub
  [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
  ☆21May 16, 2023Updated 2 years ago
• EleutherAI / bergson

  View on GitHub
  Mapping out the "memory" of neural nets with data attribution
  ☆39Updated this week
• EleutherAI / tokengrams

  View on GitHub
  Efficiently computing & storing token n-grams from large corpora
  ☆26Oct 6, 2024Updated last year
• Betswish / MIRAGE

  View on GitHub
  Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/
  ☆26Mar 10, 2025Updated 11 months ago
• epfml / getting-started

  View on GitHub
  ☆28Jan 12, 2026Updated last month
• josipjukic / alanno

  View on GitHub
  ☆36Feb 13, 2023Updated 3 years ago
• ajobi-uhc / seer

  View on GitHub
  This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …
  ☆124Feb 8, 2026Updated last week
• ApolloResearch / apd

  View on GitHub
  Attribution-based Parameter Decomposition
  ☆33Jun 11, 2025Updated 8 months ago
• mt-upc / transformer-contributions

  View on GitHub
  Measuring the Mixing of Contextual Information in the Transformer
  ☆34May 27, 2023Updated 2 years ago
• allenai / few_shot_explanations

  View on GitHub
  Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"
  ☆31Apr 28, 2023Updated 2 years ago
• Manim-Notebook / manim-notebook

  View on GitHub
  💫 ManimGL with interactive previewing in VSCode
  ☆38Apr 14, 2025Updated 10 months ago
• successar / FRESH

  View on GitHub
  ☆27Jun 12, 2023Updated 2 years ago
• ufal / factgenie

  View on GitHub
  Lightweight self-hosted span annotation tool
  ☆39Jan 20, 2026Updated 3 weeks ago
• KempnerInstitute / overcomplete

  View on GitHub
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆118Dec 4, 2025Updated 2 months ago
• sarmadgardezi / Google-Spreadsheet-Formulas

  View on GitHub
  How to add formulas to Google Spreadsheet using Google Apps Script - Sarmad Gardezi
  ☆17Apr 24, 2025Updated 9 months ago
• deckbox / wordpress_mtg_tooltips

  View on GitHub
  Wordpress plugin for Magic the Gathering that enables card tooltips and formatted deck listings.
  ☆13Dec 24, 2025Updated last month
• UPB-SS1 / PyCrowdTangle

  View on GitHub
  A Python Wrapper To Retrieve Data From The CrowdTangle API
  ☆11Jun 10, 2025Updated 8 months ago
• milesaturpin / cot-unfaithfulness

  View on GitHub
  ☆51Oct 23, 2023Updated 2 years ago
• agoldst / scuro

  View on GitHub
  R markdown format and template for light-on-dark beamer presentations—with fussy extras.
  ☆12Nov 1, 2021Updated 4 years ago
• jeremypeter / grunt-litmus

  View on GitHub
  Send email tests to Litmus using Grunt
  ☆18Feb 21, 2016Updated 9 years ago