# Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks

arXiv: https://arxiv.org/abs/2311.00288 · HTML: https://mlsanity.com/paper/2311.00288/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 1 Nov 2023.

## Builds on (most cited first, 30 of 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [Fine-tuned Language Models are Continual Learners](https://mlsanity.com/paper/2205.12393/) (2022)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Deep Active Learning for Named Entity Recognition](https://mlsanity.com/paper/1707.05928/) (2017)
- [Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://mlsanity.com/paper/1808.05697/) (2018)
- [Exploring the Benefits of Training Expert Language Models over Instruction Tuning](https://mlsanity.com/paper/2302.03202/) (2023)
- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [What to Pre-Train on? Efficient Intermediate Task Selection](https://mlsanity.com/paper/2104.08247/) (2021)
- [Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection](https://mlsanity.com/paper/2308.10819/) (2023)
- [ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization](https://mlsanity.com/paper/2201.06910/) (2022)
- [Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning](https://mlsanity.com/paper/2305.11383/) (2023)
- [Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning](https://mlsanity.com/paper/2306.01150/) (2023)
- [Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation](https://mlsanity.com/paper/2305.14327/) (2023)
- [Data-Efficient Finetuning Using Cross-Task Nearest Neighbors](https://mlsanity.com/paper/2212.00196/) (2022)
- [Evaluating the Values of Sources in Transfer Learning](https://mlsanity.com/paper/2104.12567/) (2021)

## Built on by (most cited first, 30 of 55)

- [A Survey on Data Selection for LLM Instruction Tuning](https://mlsanity.com/paper/2402.05123/) (2024)
- [A Survey of Multimodal Large Language Model from A Data-centric Perspective](https://mlsanity.com/paper/2405.16640/) (2024)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection](https://mlsanity.com/paper/2402.16705/) (2024)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric](https://mlsanity.com/paper/2502.17184/) (2025)
- [An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models](https://mlsanity.com/paper/2401.06692/) (2024)
- [D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning](https://mlsanity.com/paper/2503.11441/) (2025)
- [SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning](https://mlsanity.com/paper/2405.00705/) (2024)
- [Data Management For Training Large Language Models: A Survey](https://mlsanity.com/paper/2312.01700/) (2023)
- [Contrastive Instruction Tuning](https://mlsanity.com/paper/2402.11138/) (2024)
- [SelectLLM: Can LLMs Select Important Instructions to Annotate?](https://mlsanity.com/paper/2401.16553/) (2024)
- [Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement](https://mlsanity.com/paper/2409.11378/) (2024)
- [Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?](https://mlsanity.com/paper/2505.20903/) (2025)
- [Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model](https://mlsanity.com/paper/2404.16766/) (2024)
- [A Survey on Efficient Large Language Model Training: From Data-centric Perspectives](https://mlsanity.com/paper/2510.25817/) (2025)
- [Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression](https://mlsanity.com/paper/2402.16058/) (2024)
- [How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data](https://mlsanity.com/paper/2409.03810/) (2024)
- [Semi-supervised Fine-tuning for Large Language Models](https://mlsanity.com/paper/2410.14745/) (2024)
- [Towards Fair In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2505.09503/) (2025)
- [Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation](https://mlsanity.com/paper/2606.23127/) (2026)
- [Instruction Fusion: Advancing Prompt Evolution through Hybridization](https://mlsanity.com/paper/2312.15692/) (2023)
- [Improving Event Definition Following For Zero-Shot Event Detection](https://mlsanity.com/paper/2403.02586/) (2024)
- [Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning](https://mlsanity.com/paper/2508.21589/) (2025)
- [Importance-Aware Data Selection for Efficient LLM Instruction Tuning](https://mlsanity.com/paper/2511.07074/) (2025)
- [Baichuan Alignment Technical Report](https://mlsanity.com/paper/2410.14940/) (2024)
- [Large Language Model-guided Document Selection](https://mlsanity.com/paper/2406.04638/) (2024)
- [ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis](https://mlsanity.com/paper/2412.14809/) (2024)
- [EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness](https://mlsanity.com/paper/2502.12494/) (2025)
- [ImagebindDC: Compressing Multi-modal Data with Imagebind-based Condensation](https://mlsanity.com/paper/2511.08263/) (2025)

## Abstract (arXiv)

Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. However, how to select new tasks to improve the performance and generalizability of IT models remains an open question. Training on all existing tasks is impractical due to prohibiting computation requirements, and randomly selecting tasks can lead to suboptimal performance. In this work, we propose active instruction tuning based on prompt uncertainty, a novel framework to identify informative tasks, and then actively tune the models on the selected tasks. We represent the informativeness of new tasks with the disagreement of the current model outputs over perturbed prompts. Our experiments on NIV2 and Self-Instruct datasets demonstrate that our method consistently outperforms other baseline strategies for task selection, achieving better out-of-distribution generalization with fewer training tasks. Additionally, we introduce a task map that categorizes and diagnoses tasks based on prompt uncertainty and prediction probability. We discover that training on ambiguous (prompt-uncertain) tasks improves generalization while training on difficult (prompt-certain and low-probability) tasks offers no benefit, underscoring the importance of task selection for instruction tuning.