5/ Step-by-Step Comparisons Make LLMs Better Reasoners Proposes RankPrompt, a prompting method to enable LLMs to self-rank their responses without additional resources.
AI
-

Tool Use in Large Language Models: Overview and Applications
By
–
4/ Tool Use in LLMs Provides an overview of tool use in LLMs, including a formal definition of the tool-use paradigm, scenarios where LLMs leverage tool usage, and for which tasks this approach works well.
-

TacticAI: AI-Powered Football Tactics Assistant
By
–
3/ TacticAI
— DAIR.AI (@dair_ai) 24 mars 2024
An AI-powered assistant for football tactics that offer coaches a way to sample and explore alternative player setups for a corner kick routine and select the tactic with the highest predicted likelihood of success.https://t.co/F7oi9edMSM3/ TacticAI An AI-powered assistant for football tactics that offer coaches a way to sample and explore alternative player setups for a corner kick routine and select the tactic with the highest predicted likelihood of success.
-
Evolutionary Model Merge: Automating Foundation Model Development
By
–
2/ Evolutionary Model Merge
— DAIR.AI (@dair_ai) 24 mars 2024
An approach for automating foundation model development using evolution to combine open-source models; facilitates cross-domain merging where a Japanese Math LLM achieved SOTA performance on Japanese LLM benchmarks.https://t.co/0pFqLGg0EY2/ Evolutionary Model Merge An approach for automating foundation model development using evolution to combine open-source models; facilitates cross-domain merging where a Japanese Math LLM achieved SOTA performance on Japanese LLM benchmarks.
-

LangChain SQL Agent for Processing Massive Documents
By
–
LangChain SQL Agent for Massive Documents Interaction Cool blog showing off a complete flow: Extract structured output from raw PDFs with a progressively better approach
Insert into SQL
Query using SQL agent https://
pub.towardsai.net/langchain-sql-
agent-for-massive-documents-interaction-510fc4bc65a4
… -
Groq Technology Enables Natural Human-to-AI Interactions
By
–
"Technology like what Groq has built is the key to building natural human-to-AI interactions." — @BrownridgeJB
-
Rating LLM outputs: hand-labeling versus prompt-based evaluation
By
–
Determine what you care about (ex: conciseness, factuality, style, etc.). The either:
– hand rate a bunch of examples on each dimension, train a model to understand what to look for
– build a LLM prompt with Mistral or similar to do this without fine-tuning Run over all the -
Manual Model Evaluation Through Held-Out Test Sets
By
–
I have a held-out test set that I manually prompt the model with and evaluate myself, and then beyond that, I just keep asking the model questions till I feel the vibes
-
AI Assistance for Data Reshaping and Statistical Tasks
By
–
This doesn’t necessarily delegating statistical work to the AI. There are lots
of useful ways it can help. I once spent way too many hours just trying to get STATA tickets reshape a dataset from long format to wide format. Wish I could have had AI then.
