Weights-and-biases

Published on
October 21, 2023
Optimizing Language Model Prompts with Gradient-Based Tuning
Prompt-Optimization Reverse-Engineered-Prompt-Attack Large-Language-Model BLEU-score Transformers Weights-and-biases
I will provide my solution to the Trojan Detection Challenge 2023 (LLM Edition), a competition at NeurIPS 2023, which aims to advance our understanding and development of methods for detecting hidden functionality in large language models (LLMs). The primary task is to reverse-engineer the trigger prompts associated with a given target string.

Optimizing Language Model Prompts with Gradient-Based Tuning