8 accepted papers
Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network’s internal activations. However, SAEs are traditionally trained considering only activation values and not the effect those activations…
While large language models (LLMs) like GPT-3 have achieved impressive results on multiple choice question answering (MCQA) tasks in the zero, one, and few-shot settings, they generally lag behind the MCQA state of the art (SOTA). MCQA tasks have traditionally been presented to LLMs like cloze tasks…
Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt engineering methods require significant amounts of labeled data, ac…
We explore the idea of compressing the prompts used to condition language models, and show that compressed prompts can retain a substantive amount of information about the original prompt. For severely compressed prompts, while fine-grained information is lost, abstract information and general senti…
Large natural language models (LMs) (such as GPT-3 or T5) demonstrate impressive abilities across a range of general NLP tasks. Here, we show that the knowledge embedded in such models provides a useful inductive bias, not just on traditional NLP tasks, but also in the nontraditional task of trainin…
It is notoriously difficult to control the behavior of artificial neural networks such as generative neural language models. We recast the problem of controlling natural language generation as that of learning to interface with a pretrained language model, just as Application Programming Interfaces…
This paper demonstrates a feasible method for using a deep neural network as a sensor to estimate the attitude of a flying vehicle using only flight video. A dataset of still images and associated gravity vectors was collected and used to perform supervised learning. The network builds on a previous…
As robotic systems are deployed into everyday situations, the need for abstract reasoning becomes more pronounced. The ideal robotic assistant should be able to understand verbal commands and work independently to fulfill human-prescribed goals, even if instructions are ambiguous or circumstances ch