Challenge: Existing methods for continual instruction tuning (CIT) use pre-trained reference models, which are impractical in CIT setups since future data are unknown.
Approach: They propose an adaptive online sample selection approach that estimates each sample’s informativeness relative to all previously seen data and minimizes informative redundancy through iterative selection score updates.
Outcome: Experiments on various large foundation models show that using only 25% of the data achieves comparable performance to full-data training and outperforms the state-of-the-art sampling methods.

Similar Papers

CITB: A Benchmark for Continual Instruction Tuning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for instruction tuning do not leverage the rich natural language instructions.
Approach: They propose to use a benchmark to study how instruction tuning works in CL tasks.
Outcome: The proposed method can achieve similar or better results than existing CL methods.
Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Current data selection paradigms rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training.
Approach: They propose a dynamic sampling framework that aligns training data with the model's intrinsic competence by iterating on real-time feedback.
Outcome: Extensive experiments on eight benchmarks show that SAI-DPO outperforms static baselines at most nearly 6 points, achieving state-of-the-art efficiency with significantly less data.
InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions (2024.naacl-long)

Copied to clipboard

Challenge: In order to perform downstream tasks, Large Language Models (LLMs) need continual adaptation without catastrophic forgetting.
Approach: They propose a new paradigm that allows for continual adaptation without catastrophic forgetting . they propose to replay previous data based on task similarity with instructions .
Outcome: The proposed method improves performance over 16 tasks with different training orders.
Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent work shows that post-training datasets can be substantially downsampled without noticeably deteriorating performance.
Approach: They propose a method that efficiently bins data into groups and scores difficulty using specialized models.
Outcome: The proposed method can be efficient and universally applied to post-training datasets.
RECOST: External Knowledge Guided Data-efficient Instruction Tuning (2024.findings-acl)

Copied to clipboard

Challenge: Considering the high computing power overhead, data-efficient instruction tuning is proposed to reduce the training data size.
Approach: They propose a framework to improve instruction tuning by integrating external knowledge into a single pipeline.
Outcome: The proposed method achieves better results with only 1% of the full dataset.
Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System (2022.naacl-industry)

Copied to clipboard

Challenge: Existing continual learning methods use data replay, parameter isolation and regularization to mitigate catastrophic forgetting.
Approach: They propose a parameter-efficient continual learning framework that updates parameters offline and then trains using an online regularization method.
Outcome: The proposed framework reduces catastrophic forgetting and saves the model with the changed parameters instead of all parameters.
In-context Continual Learning Assisted by an External Continual Learner (2025.coling-main)

Copied to clipboard

Challenge: Existing continual learning methods suffer from catastrophic forgetting (CF) . Existing methods rely on fine-tuning or adapting large language models (LLMs)
Approach: They propose an approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without catastrophic forgetting (CF).
Outcome: The proposed approach outperforms existing baselines while maintaining high performance.
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for instruction tuning do not include associating instructions with existing datasets.
Approach: They propose a dynamic growth paradigm for the automatic curation of instruction-tuning data . they use existing datasets to automatically construct instruction-uning datasets .
Outcome: The proposed model reduces the API cost for generating instructions and provides high-quality data.
Coordinated Replay Sample Selection for Continual Federated Learning (2023.emnlp-industry)

Copied to clipboard

Challenge: Continual Federated Learning (CFL) combines decentralized learning with continuous learning . ubiquity of personal devices with a network connection offers rich source of data for learning problems .
Approach: They propose to combine decentralized learning with a continuous learning approach . they propose to coordinate gradient-based replay sample selection across clients .
Outcome: The proposed method shows gains early in the low replay size regime, when the budget for storing past data is small.
From Selection to Refinement: Iterative Optimization for Instruction Data (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to optimize instruction tuning datasets face two main challenges: unreasonable pruning of potentially valuable low-quality data and the persistence of noise or semantic drift during revision.
Approach: They propose an automated iterative framework for instruction data optimization that prunes low-quality data and refines low quality data using feedback-driven iteration.
Outcome: The proposed framework outperforms state-of-the-art methods on seven public benchmark datasets with high data efficiency.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations