https://github.com/ejmichaud/grokking-squared
공식 코드Towards Understanding Grokking: An Effective Theory of Representation Learning
Papers with Code 아카이브
Memorization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 3
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/elangovana/nlp-train-test-overlap-detector
공식 코드Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation
https://github.com/elempereur/wcrg
공식 코드https://github.com/elenasofia98/pme
공식 코드https://github.com/eleutherai/gpt-neox
공식 코드Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
https://github.com/eleutherai/pythia
공식 코드Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
https://github.com/eleutherai/semantic-memorization
공식 코드Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
https://github.com/emirkaan5/owl
공식 코드OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
https://github.com/epfl-dlab/broccoli
공식 코드Broccoli: Sprinkling Lightweight Vocabulary Learning into Everyday Information Diets
https://github.com/equal-mila/llm_extraction_eval
공식 코드Towards More Realistic Extraction Attacks: An Adversarial Perspective
https://github.com/eth-lre/engage-your-readers
공식 코드How to Engage Your Readers? Generating Guiding Questions to Promote Active Reading
https://github.com/eth-sri/llmprivacy
공식 코드Beyond Memorization: Violating Privacy Via Inference with Large Language Models
https://github.com/eth-sri/matharena
공식 코드MathArena: Evaluating LLMs on Uncontaminated Math Competitions
https://github.com/explanare/verbatim-memorization
공식 코드https://github.com/eyalgerman/leximark
공식 코드https://github.com/f-almeman/3d-ex
공식 코드3D-EX : A Unified Dataset of Definitions and Dictionary Examples
https://github.com/facebookresearch/QA-Overlap
공식 코드Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets
https://github.com/facebookresearch/dejavu
공식 코드Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
https://github.com/facebookresearch/dp_rdm
공식 코드DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
https://github.com/facebookresearch/dst-egqa
공식 코드Continual Dialogue State Tracking via Example-Guided Question Answering
https://github.com/facebookresearch/label_dp_antipodes
공식 코드https://github.com/facebookresearch/luckmatters
공식 코드Composing Global Optimizers to Reasoning Tasks via Algebraic Objects in Neural Nets
https://github.com/facebookresearch/mixup-cifar10
공식 코드https://github.com/facebookresearch/pitfalls-of-memorization
공식 코드The Pitfalls of Memorization: When Memorization Hurts Generalization
https://github.com/facebookresearch/task_bench
공식 코드Quantifying Adaptability in Pre-trained Language Models with 500 Tasks
https://github.com/fangyuan-ksgk/ruleeval
공식 코드https://github.com/farlit/acds
공식 코드Ancient Chinese Word Segmentation and Part-of-Speech Tagging Using Distant Supervision
https://github.com/fazalmittu/finezip
공식 코드FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
https://github.com/felixbmuller/llms-memorization-copyright
공식 코드LLMs and Memorization: On Quality and Specificity of Copyright Compliance
https://github.com/flamewei123/DEPN
공식 코드DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
https://github.com/fpour/dgb
공식 코드https://github.com/future-item/metarule-select
공식 코드Pre-Training Meta-Rule Selection Policy for Visual Generative Abductive Learning
https://github.com/gair-nlp/limo
공식 코드https://github.com/gallicch/eulerstatenetworks
공식 코드https://github.com/gamer1882/gmm
공식 코드https://github.com/gavinrbrown1/training-data-memorization
공식 코드When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.