DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]
☆19Jul 3, 2025Updated 9 months ago
Alternatives and similar repositories for DecompX
Users that are interested in DecompX are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21May 16, 2023Updated 2 years ago
- Measuring the Mixing of Contextual Information in the Transformer☆34May 27, 2023Updated 2 years ago
- ☆21Nov 26, 2022Updated 3 years ago
- ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization☆11Oct 3, 2021Updated 4 years ago
- Code for Repl4NLP paper "A Cross-Task Analysis of Text Span Representations"☆21Nov 4, 2022Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Probing and Generalization of Metaphorical Knowledge in Pre-Trained Language Modelss[ACL 2022]☆23May 15, 2022Updated 3 years ago
- Embedding language models in probability space via log-likelihood vectors☆17Apr 22, 2026Updated last week
- ☆10May 24, 2024Updated last year
- 🪝PISCES - Precise In-Parameter Suppression for Concept EraSure in Large Language Models☆12May 30, 2025Updated 11 months ago
- ☆19Updated this week
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆17Apr 25, 2021Updated 5 years ago
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)☆15Feb 24, 2026Updated 2 months ago
- Rationales for Sequential Predictions☆40Mar 10, 2022Updated 4 years ago
- ☆19Aug 30, 2025Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Find informative examples to efficiently (human)-evaluate NLG models.☆18Apr 22, 2026Updated last week
- ☆18Oct 6, 2022Updated 3 years ago
- Attribute statements generated by LLMs to preceding tokens using attention weights.☆24Apr 22, 2025Updated last year
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆28Nov 3, 2025Updated 5 months ago
- Saliency Cards are transparency documentation for saliency methods. Learn about new saliency methods or document your own!☆19Jun 9, 2023Updated 2 years ago
- Code for the paper "Refining Language Model with Compositional Explanation" (NeurIPS 2021)☆11Oct 25, 2021Updated 4 years ago
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆62May 12, 2022Updated 3 years ago
- ☆26Jun 12, 2023Updated 2 years ago
- ☆13Jul 26, 2023Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆88Apr 16, 2024Updated 2 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆26Mar 10, 2025Updated last year
- ☆11Dec 1, 2020Updated 5 years ago
- Beyond Words: A Multimodal Exploration of Persuasion in Memes☆12Jun 8, 2024Updated last year
- Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"☆30Apr 28, 2023Updated 3 years ago
- Repository for "Training Language Models To Explain Their Own Computations"☆22Dec 22, 2025Updated 4 months ago
- Code for the experiments and websites of the paper "Same Task, Different Circuits"☆35Oct 21, 2025Updated 6 months ago
- ☆16May 6, 2025Updated 11 months ago
- VertMetric: An abstractive summarization evaluation package. VERT stands for Versatile Evaluation of Reduced Texts.☆11Dec 20, 2018Updated 7 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CAT-Walk is an inducive method that learns hyperedge representations via a novel higher-order random walk, SetWalk.☆20Oct 16, 2023Updated 2 years ago
- HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking☆13Apr 11, 2025Updated last year
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Dec 27, 2022Updated 3 years ago
- Official codebase for NeurIPS 2022 paper End-to-end Learning to Index and Search in Large Output Spaces☆12Apr 19, 2023Updated 3 years ago
- Source code of ACL 2023 accepted paper "AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression"☆13Jun 14, 2023Updated 2 years ago
- ☆51Oct 23, 2023Updated 2 years ago
- Official repository for the paper: "Trees with Attention for Set Prediction Tasks" (ICML21)☆10Jan 19, 2022Updated 4 years ago