Language models are weak learners
A central notion in practical and theoretical machine learning is that of a weak learner,
classifiers that achieve better-than-random performance (on any given distribution over …
classifiers that achieve better-than-random performance (on any given distribution over …
Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
Prompt tuning in natural language processing (NLP) has become an increasingly popular
method for adapting large language models to specific tasks. However, the transferability of …
method for adapting large language models to specific tasks. However, the transferability of …
Unnatural language processing: How do language models handle machine-generated prompts?
Language model prompt optimization research has shown that semantically and
grammatically well-formed manually crafted prompts are routinely outperformed by …
grammatically well-formed manually crafted prompts are routinely outperformed by …
Latent Communication in Artificial Neural Networks
L Moschella - arxiv preprint arxiv:2406.11014, 2024 - arxiv.org
As NNs permeate various scientific and industrial domains, understanding the universality
and reusability of their representations becomes crucial. At their core, these networks create …
and reusability of their representations becomes crucial. At their core, these networks create …
STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
Interactive fiction games have emerged as an important application to improve the
generalization capabilities of language-based reinforcement learning (RL) agents. Existing …
generalization capabilities of language-based reinforcement learning (RL) agents. Existing …
[HTML][HTML] Out-of-distribution generalisation in machine learning
A Słowik - 2023 - repository.cam.ac.uk
Abstract Machine learning has proven extremely useful in many applications in recent years.
However, a lot of these success stories stem from evaluating the algorithms on data very …
However, a lot of these success stories stem from evaluating the algorithms on data very …