9/ Making LLMs Better at Dense Retrieval – proposes LLaRA which adapts an LLM for dense retrieval; LLaMa-2-7B was improved on benchmarks like MSMARCO and BEIR.
@dair_ai
-
Gemini vs GPT-4V: Vision-Language Models Comparison
By
–
10/ Gemini vs. GPT-4V – a comparison of vision-language models like Gemini & GPT-4V; finds that GPT-4V is precise and succinct in responses, while Gemini excels in providing detailed, expansive answers accompanied by relevant imagery and links.
-
Survey of Reasoning with Foundation Models: Latest Advancements
By
–
8/ A Survey of Reasoning with Foundation Models – provides a comprehensive survey of seminal foundational models for reasoning, highlighting the latest advancements in various reasoning tasks, methods, benchmarks, and potential future directions.
-
26 Principles for Optimizing LLM Prompts and Instructions
By
–
7/ Principled Instructions Are All You Need – introduces 26 principles to streamline the process of querying and prompting LLMs; conducts extensive experiments on LLaMA-1/2 & GPT-3.5/4 to verify their effectiveness on instructions & prompts design.
-
Math-Centric Corpus for Generative AI Foundation Models
By
–
6/ Generative AI for Math – presents a diverse and high-quality math-centric corpus comprising of ~9.5 billion tokens to train foundation models.
-
MLP Layers as Lookup Tables for Factual Recall in LLMs
By
–
5/ Fact Recalling in LLMs – studies how MLP layers implement a lookup table for factual recall; suggests that early MLP layers act as a lookup table and recommends thinking about the recall of factual knowledge in the model as multi-token embeddings.
-
PromptBench: Unified LLM Evaluation and Prompt Engineering Library
By
–
3/ PromptBench – a unified library that supports comprehensive evaluation and analysis of LLMs; it consists of functionalities for prompt construction, prompt engineering, dataset and model loading, adversarial prompt attack, and more.
-
Red-teaming GPT-4 APIs: Fine-tuning, Functions, Retrieval
By
–
4/ Exploiting Novel GPT-4 APIs – performs red-teaming on three functionalities exposed in the GPT-4 APIs: fine-tuning, function calling, and knowledge retrieval.
-
Survey of 300+ Papers: Generative AI from Gemini to Q-Star
By
–
2/ From Gemini to Q-Star – surveys 300+ papers and summarizes research developments to look at in the space of Generative AI; it covers computational challenges, scalability, real-world implications, and more.
-
Pearl: Production-Ready RL Agent Software Package Released
By
–
9/ Pearl – introduces a new production-ready RL agent software package that enables researchers and practitioners to develop RL AI agents that adapt to environments with limited observability, sparse feedback, and high stochasticity.