AI Paper Atlas

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

SPICE: Submodular Penalized Information–Conflict Selection for Efficient Large Language Model Training

Powei Chang, Jinpeng Zhang, Bowen Chen, Chenyu Wang, Chenlu Guo, Yixing Zhang, Yukang Gao, JianXiang Xiang, Yue Gao, Chaoqun Sun, Yiyi Chen, Dongying kong

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 3 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% data with SPICE instead of training on full dataQwen2-7B LoRA instruction tuning · 8-benchmark averageaverage score: 56.4 -> 58.0Improved
select 10% data with SPICE instead of training on full dataLLaMA2-7B LoRA instruction tuning · 8-benchmark averageaverage score: 30.8 -> 31.1Improved
use SPICE instead of LESSQwen2-7B · 8-benchmark averageaverage score: 55.2 -> 58.0Improved
use SPICE instead of DPPQwen2-7B · 8-benchmark averageaverage score: 57.0 -> 58.0Improved
use SPICE instead of random 10% selectionQwen2-7B · IFEvalscore: 28.3 -> 38.6Improved
use SPICE instead of full dataLLaMA2-7B · TruthfulQAscore: 43.5 -> 40.3Hurt
use SPICE instead of full dataQwen2-7B · BBHscore: 61.3 -> 61.0No clear effect
add conflict penalty lambda greater than 0 to greedy log-det FIM selection (ablation)SPICE · 8 benchmarksperformanceImproved
use larger 7B proxy model instead of 0.5B or 1.5B Qwen2 proxy (ablation)SPICE · 8 benchmarksaverage score: +0.1 averageNo clear effect
use LLaMA2-style proxy instead of Qwen2 proxy to select data for Qwen2-7B (ablation)SPICE · Qwen2-7BaccuracyHurt
use adaptive early stopping SPICE+ instead of fixed budget (ablation)SPICE · benchmarksaccuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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