Contrastive Chain-of-Thought Prompting
Paper
•
2311.09277
•
Published
•
34
Some of the Papers I've Read
A few of the research papers that I've read.
Note To make LLM reasoning more effective extend Chain of Thought prompting to include both positive and negative examples in the prompt. The paper shows how this creates better outcomes and also demonstrates some techniques for creating negative examples
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Paper • 2201.11903 • Published • 9 -
Orca 2: Teaching Small Language Models How to Reason
Paper • 2311.11045 • Published • 70 -
System 2 Attention (is something you might need too)
Paper • 2311.11829 • Published • 39 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 47 -
Tuning Language Models by Proxy
Paper • 2401.08565 • Published • 20 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 27 -
RAG Does Not Work for Enterprises
Paper • 2406.04369 • Published • 1