DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)
Copied to clipboard
| Challenge: | Several studies rely on additional models to optimize mixtures. |
| Approach: | They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup. |
| Outcome: | The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling. |
Similar Papers
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts (2025.naacl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) models are constrained by their fixed model capacities when the number of tasks grows in instruction tuning. |
| Approach: | They propose to combine all training tasks and apply fixed sampling weights without considering the importance of different tasks as the model training state changes. |
| Outcome: | The proposed method can be used on knowledge & reasoning tasks and open-ended queries with limited training budget. |
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. |
SMART: Submodular Data Mixture Strategy for Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine tuning language models are manual or rely on intuition. |
| Approach: | They propose a method which uses a submodular function to assign importance scores to tasks and then use them to determine mixture weights. |
| Outcome: | The proposed method outperforms traditional methods such as examples proportional mixing and equal mixing. |
Demystifying Instruction Mixing for Fine-tuning Large Language Models (2024.acl-srw)
Copied to clipboard
| Challenge: | Instruction tuning is effective for aligning large language models with human instructions, but the procedure to optimizing the mixing of instruction datasets is still unclear. |
| Approach: | They categorize instructions into three primary types: NLP downstream tasks, coding, and general chat. |
| Outcome: | The proposed method improves performance of large language models (LLMs) but it is difficult to combine different instruction datasets to optimize overall performance. |
Instruction Tuning with Human Curriculum (2024.findings-naacl)
Copied to clipboard
| Challenge: | a recent study shows that human curriculum-inspired strategies can enhance performance of large language models. |
| Approach: | They propose a method for generating instruction-response datasets that emulate human learning . they find that substantial improvements can be achieved through curriculum ordering . |
| Outcome: | The proposed method achieves performance improvements on truthfulQA, MMLU, OpenbookQA, and ARC-hard benchmarks without additional computational costs. |
Federated Data-Efficient Instruction Tuning for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing federated learning (FL) uses all local data, causing excessive computational overhead and overfitting to local data. |
| Approach: | They propose a federated data-efficient instruction tuning approach which utilizes a representative subset of edge-side data to tune LLMs. |
| Outcome: | The proposed method improves Rouge-L on unseen tasks by 10.72% over the SOTA full-data instruction tuning methods while using less than 1.5% of the data samples. |
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated considerable proficiency in general natural language processing tasks. |
| Approach: | They propose a parameter-efficient sparsity crafting method which crafts dense models into sparse models using the mixture-of-experts architecture. |
| Outcome: | The proposed method significantly reduces computational costs and GPU memory requirements, while maintaining the quality of approximation in function space. |
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)
Copied to clipboard
Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu
| Challenge: | Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. |
| Approach: | They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR). |
| Outcome: | The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations. |
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. |
SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe (2026.acl-long)
Copied to clipboard
| Challenge: | Efforts to improve instruction tuning often focus on higher-quality supervised fine-tuning datasets, typically requiring data filtering with proprietary LLMs or human annotation. |
| Approach: | They propose a Mixup-based recipe that elevates LLM instruction tuning without relying on well-curated datasets. |
| Outcome: | The proposed model improves instruction-following and healthcare-specific tasks with consistent improvements across LLM families and SFT datasets. |