Post-hoc interpretability for neural nlp: A survey
Neural networks for NLP are becoming increasingly complex and widespread, and there is a
growing concern if these models are responsible to use. Explaining models helps to address …
growing concern if these models are responsible to use. Explaining models helps to address …
Probing classifiers: Promises, shortcomings, and advances
Y Belinkov - Computational Linguistics, 2022 - direct.mit.edu
Probing classifiers have emerged as one of the prominent methodologies for interpreting
and analyzing deep neural network models of natural language processing. The basic idea …
and analyzing deep neural network models of natural language processing. The basic idea …
Bloom: A 176b-parameter open-access multilingual language model
Large language models (LLMs) have been shown to be able to perform new tasks based on
a few demonstrations or natural language instructions. While these capabilities have led to …
a few demonstrations or natural language instructions. While these capabilities have led to …
Locating and editing factual associations in GPT
We analyze the storage and recall of factual associations in autoregressive transformer
language models, finding evidence that these associations correspond to localized, directly …
language models, finding evidence that these associations correspond to localized, directly …
Do vision transformers see like convolutional neural networks?
Convolutional neural networks (CNNs) have so far been the de-facto model for visual data.
Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or …
Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Fast model editing at scale
While large pre-trained models have enabled impressive results on a variety of downstream
tasks, the largest existing models still make errors, and even accurate predictions may …
tasks, the largest existing models still make errors, and even accurate predictions may …
[HTML][HTML] Pre-trained models: Past, present and future
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …
great success and become a milestone in the field of artificial intelligence (AI). Owing to …
Lasuie: Unifying information extraction with latent adaptive structure-aware generative language model
Universally modeling all typical information extraction tasks (UIE) with one generative
language model (GLM) has revealed great potential by the latest study, where various IE …
language model (GLM) has revealed great potential by the latest study, where various IE …
Autoprompt: Eliciting knowledge from language models with automatically generated prompts
The remarkable success of pretrained language models has motivated the study of what
kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the …
kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the …