Related papers: Prompt-MII: Meta-Learning Instruction Induction for LLMs

Prompt-MII: Meta-Learning Instruction Induction for LLMs

URL: http://arxiv.org/abs/2510.16932v2
Date: Fri, 31 Oct 2025 02:00:58 GMT
Title: Prompt-MII: Meta-Learning Instruction Induction for LLMs
Authors: Emily Xiao, Yixiao Zeng, Ada Chen, Chin-Jou Li, Amanda Bertsch, Graham Neubig,
Abstract summary: In this paper we propose a method to perform instruction induction, where we take training examples and reduce them to a compact but descriptive prompt.<n>We train on over 3,000 diverse classification datasets from the HuggingFace hub, and evaluate on 90 unseen tasks.<n> PROMPT-MII improves downstream model quality by 4-9 F1 points (10-20% relative), matching ICL performance while requiring 3-13x fewer tokens.
Score: 40.37193886125562
License: http://creativecommons.org/licenses/by/4.0/
Abstract: A popular method to adapt large language models (LLMs) to new tasks is in-context learning (ICL), which is effective but incurs high inference costs as context length grows. In this paper we propose a method to perform instruction induction, where we take training examples and reduce them to a compact but descriptive prompt that can achieve performance comparable to ICL over the full training set. Specifically, we propose PROMPT-MII, a reinforcement learning (RL) based framework to meta-learn an instruction induction model that can generate compact instructions on the fly for an arbitrary new dataset. We train on over 3,000 diverse classification datasets from the HuggingFace hub, and evaluate on 90 unseen tasks. PROMPT-MII improves downstream model quality by 4-9 F1 points (10-20% relative), matching ICL performance while requiring 3-13x fewer tokens.

Related papers

CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs [81.79228604962687]
This work investigates whether small-scale LMs can benefit from instruction tuning.<n>We compare conversational and question-answering instruction tuning datasets, applied either in a merged or sequential curriculum.<n>Results show that instruction tuning yields small but consistent gains in fine-tuning scenarios, with sequential curricula outperforming merged data.<n>However, improvements do not consistently transfer to zero-shot tasks, suggesting a trade-off between interaction-focused adaptation and broad linguistic generalization.
arXiv Detail & Related papers (2025-10-29T10:36:39Z)
Large Language Models are Demonstration Pre-Selectors for Themselves [57.101804269100185]
In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data.<n>FEw yet Essential Demonstration prE-selectoR is a novel pre-selection framework that identifies a representative subset of demonstrations.<n>FEw yet Essential Demonstration prE-selectoR can reduce training data size by over 20% while maintaining performance.
arXiv Detail & Related papers (2025-06-06T12:29:03Z)
Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods [69.36397993451742]
This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss.
arXiv Detail & Related papers (2024-10-22T17:45:47Z)
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z)
Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation [56.75665429851673]
This paper introduces a novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment.<n>Experiments demonstrate that we can maintain or even improve model performance by compressing synthetic multimodal instructions by up to 90%.
arXiv Detail & Related papers (2024-09-27T08:20:59Z)
Instruction Tuning With Loss Over Instructions [42.9106826952674]
Instruction Modelling (IM) trains LMs by applying a loss function to the instruction and prompt part rather than solely to the output part. We show that, in many scenarios, IM can effectively improve the LM performance on both NLP tasks and open-ended generation benchmarks. Remarkably, in the most advantageous case, IM boosts model performance on AlpacaEval 1.0 by over 100%.
arXiv Detail & Related papers (2024-05-23T10:12:03Z)
Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
arXiv Detail & Related papers (2023-02-22T17:44:15Z)
Boosting Natural Language Generation from Instructions with Meta-Learning [43.64522457686405]
Recent work has shown that language models (LMs) trained with multi-task. textitinstructional learning (MTIL) can solve diverse NLP. tasks with improved performance compared to prompt tuning. In this paper we investigate whether meta-learning applied to MTIL can further improve generalization to unseen tasks in a zero-shot setting.
arXiv Detail & Related papers (2022-10-20T22:23:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.