Initializing a new thread on the very best, must read, well-written, papers on Large Language Model capabilities, limits, and use. We’re all balancing ‘do I continue my own work’ vs ‘do I keep up with the literature so my work stays cutting-edge and relevant, and I don’t waste my time re-inventing t…

Similar to the “tree of thoughts” paper, here’s “graph of thoughts”: [image] Graph of Thoughts: Solving Elaborate Problems with Large Language Models We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offer…

Welcome posters of papers! I want to remind forum members that posts to this thread should be the links to the paper and a brief summary of the paper only. Please use the accompanying discussion breakout thread to discus papers of interest [image] Discussion thread for "Foundatio…

Some stuff I run across isn’t necessarily ‘foundational’ and the depth isn’t always that extensive (at least math wise), but it talks about an idea that I’m interested in which perhaps doesn’t lend itself to formal exploration - when few other papers will. Probably because it’s hard to measure prec…

Recently have engaged in some RAG / retrieval augmented generation. [2307.03172] Lost in the Middle: How Language Models Use Long Contexts [2004.04906] Dense Passage Retrieval for Open-Domain Question Answering [2309.09117] Contrastive Decoding Improves Reasoning in Large Language Models [2209…

Amazing read! I am trying out the prompt examples myself as explained in the experiment and it gives slightly different answers but defenitly proves their point that Chatgpt 4 is thinking or it looks like it is thinking like a human. Very impressive indeed! Thanks for sharing.

[image] Textbooks Are All You Need We introduce phi-1, a new large language model for code, with significantly smaller size than competing models: phi-1 is a Transformer-based model with 1.3B parameters, trained for 4 days on 8 A100s, using a selection of ``textbook quality" data from... …

I see a paper where it says LLM can do time series forecasting. Is it really possible based on the architecture on which it has been built? The paper is here 2306.11025.pdf 231.37 KB

[image] NEFTune: Noisy Embeddings Improve Instruction Finetuning We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard finetuning of LLaMA-2-7B using Alpaca achieve…

[image] Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in... Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-output examples without an…

Online dynamical learning and sequence memory with neuromorphic nanowire networks https://www.nature.com/articles/s41467-023-42470-5 Nanowire Networks (NWNs) belong to an emerging class of neuromorphic systems that exploit the unique physical properties of nanostructured materials. In addition to…

Foundational must read GPT/LLM papers

Community

Topic		Replies	Views
Discussion thread for "Foundational must read GPT/LLM papers" Community gpt-4 , gpt-35-turbo , chatgpt , research	75	12534	September 3, 2024
Personalized Memory and Long-Term Relationship with AI: Customization and Continuous Evolution ChatGPT gpt-4 , chatgpt , assistants-api	33	1570	March 21, 2025
2-shot plus step-by-step prompts for gpt-3.5-turbo performance at gpt-4 level? Prompting gpt-4	32	8920	May 8, 2023
Biggest difficulty in developing LLM apps API development	75	8551	January 12, 2024
Share: Fine-Tune GPT 3.5 16k Results Only 10 Examples Novel Outlines API fine-tuning , api , tp-1 , authors	24	4785	February 4, 2024

Foundational must read GPT/LLM papers

Related topics