A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)
Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task. Despite growing interest, the literature on targeted instruction selection remains fragmented and opaque: methods vary widely in selection budgets, often omit zero-shot baselines, and frequently entangle the contributions of key components. As a result, practitioners lack actionable guidance on selecting instructions for their target tasks. In this work, we aim to bring clarity to this landscape by disentangling and systematically analyzing the two core ingredients: data representation and selectio...
| Authors | Nihal V. Nayak, Paula Rodriguez-Diaz, Neha Hulkund et al. |
|---|---|
| Primary category | cs.LG |
| Published | 16 February 2026 |
| Last updated at source | 18 June 2026 |
Connected in the knowledge graph
- Harvard-DCML/tis-subset-datasets-Llama-2-7b-hfDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.