From Task Affinities to Optimal Allocations: Probabilistic Graphical Modelling for Supervised Finetuning
cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
- Efficient Data Representation by Selecting Prototypes with Importance Weights
- Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- RegMix: Data Mixture as Regression for Language Model Pre-training
- D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning
- Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
- Multitask Prompted Training Enables Zero-Shot Task Generalization
- Llama 2: Open Foundation and Fine-Tuned Chat Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis