8/ Prompt Injection Threats – a comprehensive analysis of novel prompt injection threats to application-integrated LLMs.
@dair_ai
-
Modular Deep Learning Survey: Building Blocks Neural Networks
By
–
5/ Modular Deep Learning – a survey offering a unified view of the building blocks of modular neural networks; it also includes a discussion about modularity in the context of scaling LMs, causal inference, and other key topics in ML.
-
Recitation-Augmented LMs Enhance Knowledge-Intensive Task Performance
By
–
6/ Recitation-Augmented LMs – an approach that recites passages from the LLM’s own memory to produce final answers; shows high performance on knowledge-intensive tasks.
-
Top ML Papers Week: LLaMA, Diffusion Models, Code Optimization
By
–
Top ML Papers of the Week (Feb 20-26): – LLaMA (65B params foundation model)
– Composer (5B params diffusion model)
– Active-Prompt
– Modular Deep Learning
– Memory-Efficient Radiance Fields
– LLMs to Optimize Code … -
LLaMA 65B: Meta’s Open Source Model Outperforms GPT-3
By
–
1/ LLaMA – a 65B parameter foundation model released by Meta AI; relies on publicly available data and outperforms GPT-3 on most benchmarks despite being 10x smaller.
-
Composer: 5B Parameter Creative Diffusion Model for Text-Image Generation
By
–
2/ Composer – a 5B parameter creative and controllable diffusion model trained on billions (text, image) pairs.
-
Prompt Engineering Guide Trends on Hacker News
By
–
Prompt Engineering Guide (3.5K) Our prompt engineering guide is trending on Hacker News! Thanks for all the support. Do check it out if you want to learn more about how to make the best use of LLMs. https://
github.com/dair-ai/Prompt
-Engineering-Guide
… -
Energy Transformer: Replacing Feedforward Blocks with Associate Memory
By
–
10). Energy Transformer – a transformer architecture that replaces the sequence of feedforward transformer blocks with a single large Associate Memory model; this follows the popularity that Hopfield Networks have gained in the field of ML.
-
Augmented Language Models: Reasoning Skills and Tool Integration Survey
By
–
7). Augmented Language Models – a survey of language models that are augmented with reasoning skills and the capability to use tools.
-
Auditing Large Language Models: Policy Framework Proposal
By
–
9) Auditing large language models – proposes a policy framework for auditing LLMs.