Research map / Large language models / Instruction and fine-tuning
HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models
Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add both global and local actors to proportional sampling (ablation) | Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 46.25 -> 48.07 | Improved |
| add local actors on top of the global actor (ablation) | HBO Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 47.22 -> 48.07 | Improved |
| add global actor on top of the local actors (ablation) | HBO Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 47.46 -> 48.07 | Improved |
| use 4 difficulty groups instead of 1, 2, 8 or 16 (ablation) | HBO Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 47.22 (1 group) -> 48.07 (4 groups); 47.45 (8), 47.87 (16) | Improved |
| discard the easiest training examples while holding compute fixed (ablation) | HBO Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 48.07 -> 47.41 (25%), 47.08 (50%), 46.55 (75%) | Hurt |
| use PPL ratio local reward with L2-norm global reward instead of PPL or loss rewards (ablation) | HBO · Multilingual (5 tasks avg) | accuracy: 46.94 (PPL) / 47.22 (Loss) -> 48.07 | Improved |
| use CosSim instead of L2 norm for the global reward (ablation) | HBO · Multilingual (5 tasks avg) | accuracy: 48.07 -> 47.69 | Hurt |
| use PPL or loss instead of SuperFiltering to split difficulty groups (ablation) | HBO · Multilingual (5 tasks avg) | accuracy: 48.07 -> 47.42 (PPL), 47.23 (Loss) | Hurt |
| scale model size from 1B to 3B to 8B (ablation) | HBO vs proportional sampling · Multilingual (5 tasks avg) | accuracy gain: +0.40 (1B), +1.25 (3B), +1.83 (8B) | Improved |
| use HBO instead of DMT or EVIC data-mixing baselines | Llama-3.1-8B · Multilingual (5 tasks avg) | accuracy: 45.43 (DMT), 46.10 (EVIC) -> 48.07 | Improved |
| use HBO with only 20% of training data | Llama-3.1-8B · Multilingual | accuracy: +3.50 over Prop. | Improved |
| update global and local actors every 200 steps rather than more frequently (ablation) | HBO · Multilingual | performance and runtime: about 15% additional training overhead | Improved |
Closest papers by meaning
- Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models (ICML 2025 · similarity 0.90)
- When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method (ICLR 2024 · similarity 0.89)
- Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data (NeurIPS 2025 · similarity 0.89)
- Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning (NeurIPS 2025 · similarity 0.88)
- Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs (ICLR 2024 · similarity 0.88)
- DELIFT: Data Efficient Language model Instruction Fine-Tuning (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
