pith. sign in

GrIPS: Gradient-free, edit-based instruction search for prompting large language models

Grips: Gradient-free, edit-based instruction search for prompting large language models , author= · 2023 · arXiv 2203.07281

4 Pith papers cite this work. Polarity classification is still indexing.

4 Pith papers citing it
read on arXiv browse 4 citing papers

citation-role summary

background 2

citation-polarity summary

background 2

fields

cs.CL 2 cs.LG 2

years

2026 1 2023 2 2022 1

verdicts

UNVERDICTED 4

roles

background 2

polarities

background 2

representative citing papers

Learning, Fast and Slow: Towards LLMs That Adapt Continually

cs.LG · 2026-05-12 · unverdicted · novelty 7.0 · 2 refs

Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.

Large Language Models as Optimizers

cs.LG · 2023-09-07 · unverdicted · novelty 7.0

Large language models can optimize by being prompted with histories of past solutions and scores to propose better ones, producing prompts that raise accuracy up to 8% on GSM8K and 50% on Big-Bench Hard over human-designed baselines.

citing papers explorer

Showing 4 of 4 citing papers.

  • Learning, Fast and Slow: Towards LLMs That Adapt Continually cs.LG · 2026-05-12 · unverdicted · none · ref 44 · 2 links

    Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.

  • EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers cs.CL · 2023-09-15 · unverdicted · none · ref 123

    EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.

  • Large Language Models as Optimizers cs.LG · 2023-09-07 · unverdicted · none · ref 27

    Large language models can optimize by being prompted with histories of past solutions and scores to propose better ones, producing prompts that raise accuracy up to 8% on GSM8K and 50% on Big-Bench Hard over human-designed baselines.

  • Ignore Previous Prompt: Attack Techniques For Language Models cs.CL · 2022-11-17 · unverdicted · none · ref 22

    PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.