AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Neuron-Aware Data Selection in Instruction Tuning for Large Language Models

Xin Chen, Junchao Wu, Shu Yang, Runzhe Zhan, Zeyu Wu, Min Yang, Shujian Huang, Lidia S. Chao, Derek F. Wong

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Instruction data selection · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
select 10% of Alpaca-GPT4 with NAIT (all features) instead of training on full dataLLaMA-2-7b · 9-benchmark averageaverage score: 36.03 -> 37.20 (+3.24%)Improved
select data using GSM activation featuresLLaMA-2-7b · 9-benchmark averageaverage score: 36.03 -> 37.70 (+4.65%)Improved
use NAIT selection instead of AlpaGasusLLaMA-2-7b · 9-benchmark averageaverage score: 35.18 -> 37.20Improved
use NAIT (all features) instead of SelectITLLaMA-2-7b · 9-benchmark averageaverage score: 37.16 -> 37.20No clear effect
choose top 10% highest-alignment samples instead of random (ablation)LLaMA-2-7b · 5-task averageaverage score: 34.04 -> 35.18Improved
choose lowest-alignment samples instead of random (ablation)LLaMA-2-7b · 5-task averageaverage score: 34.04 -> 28.27Hurt
apply NAIT selection on LLaMA-2-13b (ablation)LLaMA-2-13b · 5-task averageaverage score: 40.76 -> 42.53 vs randomImproved
apply NAIT selection on Mistral-7b (ablation)Mistral-7b · 5-task averageaverage score: 37.69 -> 41.43 vs randomImproved
apply NAIT selection on Llama-3-8b (ablation)Llama-3-8b · 5-task averageaverage score: 52.10 -> 57.63 vs randomImproved
apply NAIT selection on Qwen-2.5-7b (ablation)Qwen-2.5-7b · 5-task averageaverage score: 73.39 -> 75.20 vs randomImproved
increase selected fraction beyond 30% up to 100% (ablation)NAIT · Alpaca-GPT4performanceHurt
increase number of in-domain examples (ablation)NAIT · GSM and TydiQAscore: peaks 18.35 (GSM) and 47.57 (TydiQA) at 4096Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy