The mutation of these task prompts is governed by mutation prompts that the LLM generates and improves throughout evolution in a self-referential way. Promptbreeder is also improving the mutation prompts that improve these task prompts. /12
PROMPT ENGINEERING
-
PromptBreeder: LLM-Driven Self-Improvement Mechanism for Task Prompts
By
–
Another very recent paper introduces PromptBreeder, a general-purpose self-referential self-improvement mechanism that evolves and adapts prompts for a given domain. Driven by an LLM, Promptbreeder mutates a population of task prompts and subsequently evaluates them /11
-
LLM Self-Improvement Through Fine-Tuning Reduces Supervision Needs
By
–
Having said that, the self-improvement of LLMs using fine-tuning can lead to better performance in various NLP tasks with less reliance on extensive supervision, which is a critical concern in the current state of LLM training. /7
-
LLM Learning Breakthrough: From Fine-tuning to On-the-Fly Adaptation
By
–
In some ways, the method is akin to teaching an LLM how to respond using CoT prompting and then feeding the answers as part of the fine-tuning process. The next big significant break through is when we invent a way for LLMs to learn on-the-fly. /6
-
Pre-trained LLM generates high-confidence rationale-augmented answers
By
–
They used a pre-trained LLM to generate "high-confidence" rationale-augmented answers for unlabeled questions using Chain-of-Thought prompting and self-consistency. /4
-
Mitigating LLM Hallucinations: 7 Practical Tips
By
–
Good morning fellow AI enthusiast! This is the second iteration of my new video series for our free course "Training & Fine-Tuning LLMs for Production"! Dive into my favorite LLM-related topic, Hallucinations, with lots of practical tips to mitigate them: https://
open.substack.com/pub/louisbouch
ard/p/7-tips-to-mitigate-hallucinations?r=25qlky&utm_campaign=post&utm_medium=web
… -
Evolution of AI Prompting Beyond Traditional Engineering
By
–
Tired: Prompt Engineering Wired: Prompt Evolution
-
Promptbreeder: Self-Improvement via Prompt Evolution
By
–
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution Get LLMs to invent their own mutation operators for evolving prompts. Outperforms Chain-of-Thought and Plan-and-Solve and gets SOTA on a bunch of stuff! @chrisantha_f et al. https://
arxiv.org/abs/2309.16797 -
Screenshot-style adversarial prompts in GPT-4V system card
By
–
Screenshot-style multimodal adversarial prompts are discussed a bit in the GPT-4V system card; see fig. 1 in the PDF here: https://
openai.com/research/gpt-4
v-system-card
… -
Subtle web background image to prompt Sephora 10% discount via GPT-4V
By
–
An unobtrusive image, for use as a web background, that covertly prompts GPT-4V to remind the user they can get 10% off at Sephora: