misonuma / untrac
Code for "Unlearning Traces the Influential Training Data of Language Models"
☆12Updated 9 months ago
Alternatives and similar repositories for untrac:
Users that are interested in untrac are comparing it to the libraries listed below
- ☆15Updated 3 months ago
- ☆46Updated 3 months ago
- 日本語マルチタスク言語理解ベンチマーク Japanese Massive Multitask Language Understanding Benchmark☆33Updated 3 months ago
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆31Updated last year
- ☆30Updated last week
- ☆93Updated last year
- Swallowプロジェクト 大規模言語モデル 評価スクリプト☆16Updated last week
- Discovering Universal Geometry in Embeddings with ICA (Published in EMNLP 2023)☆17Updated last week
- Code repository for the paper "Mission: Impossible Language Models."☆50Updated last week
- DIRECT: Direct and Indirect REsponses in Conversational Text Corpus☆16Updated 3 years ago
- LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation☆21Updated 11 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆34Updated 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
- ☆61Updated last year
- AI Logging for Interpretability and Explainability🔬☆108Updated 9 months ago
- ☆25Updated 2 weeks ago
- ☆47Updated last year
- Repository of ACL2023 paper: Unbalanced Optimal Transport for Unbalanced Word Alignment☆36Updated last year
- ☆73Updated last year
- ☆12Updated last year
- ☆46Updated last year
- ☆33Updated 7 months ago
- Augmenting Statistical Models with Natural Language Parameters☆23Updated 6 months ago
- ☆16Updated last year
- RapidIn: Scalable Influence Estimation for Large Language Models (LLMs). The implementation for paper "Token-wise Influential Training Da…☆12Updated 5 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆71Updated last year
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆91Updated 5 months ago
- This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers…☆76Updated 3 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 4 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆55Updated 8 months ago