MadryLab / AT2Links
Attribute statements generated by LLMs to preceding tokens using attention weights.
☆13Updated last month
Alternatives and similar repositories for AT2
Users that are interested in AT2 are comparing it to the libraries listed below
Sorting:
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆38Updated 2 years ago
- Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"☆48Updated 3 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆24Updated 2 months ago
- ☆44Updated last year
- Landing page for MIB: A Mechanistic Interpretability Benchmark☆11Updated this week
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆21Updated 9 months ago
- The geometry of multilingual language model representations (EMNLP 2022).☆21Updated 2 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆21Updated 4 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Updated last year
- Measuring the Mixing of Contextual Information in the Transformer☆29Updated 2 years ago
- ☆26Updated last week
- Code associated with the paper: "Few-Shot Self-Rationalization with Natural Language Prompts"☆13Updated 3 years ago
- A curated list of research papers and resources on Cultural LLM.☆44Updated 8 months ago
- This is the official implementation for our ACL 2024 paper: "Causal Estimation of Memorisation Profiles".☆21Updated 2 months ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆41Updated last year
- Codebase for running (conditional) probing experiments☆22Updated 2 years ago
- ☆34Updated 3 years ago
- Query-focused summarization data☆41Updated 2 years ago
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆62Updated 3 years ago
- ☆20Updated 3 months ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Updated 4 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆76Updated last year
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆31Updated 3 years ago
- Research code for the paper "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models"☆27Updated 3 years ago
- Codes for "Benchmarking the Generation of Fact Checking Explanations"☆10Updated 9 months ago
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21Updated 2 years ago
- Code for the paper "REV: Information-Theoretic Evaluation of Free-Text Rationales"☆15Updated last year
- A software for transferring pre-trained English models to foreign languages☆18Updated 2 years ago
- https://arxiv.org/abs/2404.10917☆14Updated 2 months ago
- ☆31Updated last year