Search Results for author:
Found 13 papers, 10 papers with code
Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
System-prompting is a standard tool for customizing language-model chatbots, enabling them to follow a specific instruction.
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
Latent diffusion models (LDMs) exhibit an impressive ability to produce realistic images, yet the inner workings of these models remain mysterious.
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
This intervention significantly improves the performance of LLaMA models on the TruthfulQA benchmark.
AttentionViz: A Global View of Transformer Attention
Transformer models are revolutionizing machine learning, but their inner workings remain mysterious.
The System Model and the User Model: Exploring AI Dashboard Design
We conjecture that, for many systems, the two most important models will be of the user and of the system itself.
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Language models show a surprising range of capabilities, but the source of their apparent competence is unclear.
An Interpretability Illusion for BERT
We describe an "interpretability illusion" that arises when analyzing the BERT model.
Visualizing and Measuring the Geometry of BERT
Transformer architectures show significant promise for natural language processing.
XRAI: Better Attributions Through Regions
Saliency methods can aid understanding of deep neural networks.
GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology.
TCAV: Relative concept importance testing with Linear Concept Activation Vectors
In particular, this framework enables non-machine learning experts to express concepts of interests and test hypotheses using examples (e. g., a set of pictures that illustrate the concept).
SmoothGrad: removing noise by adding noise
Explaining the output of a deep network remains a challenge.
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
In addition to improving the translation quality of language pairs that the model was trained with, our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation.
