https://github.com/Jayfeather1024/Backdoor-Enhanced-Alignment
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.
Large language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model.
Source: Wikipedia
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
Text-based classification of interviews for mental health -- juxtaposing the state of the art
Conformer: Convolution-augmented Transformer for Speech Recognition
BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model
Universal Language Model Fine-tuning for Text Classification
MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science
MPNet: Masked and Permuted Pre-training for Language Understanding
CTRL: A Conditional Transformer Language Model for Controllable Generation
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.