AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection

Kexian Tang, Jiani Wang, Shaowen Wang, Kaifeng Lyu

ICML 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 0 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
scale synthetic data with SPA from small to 120M tokensSPA on Qwen2.5-7B · SQuADQA accuracy (%): 58.2% (5 samples) -> 70.74% (27 samples) -> 91.27% (120M tokens)Improved
RL-trained generator (SEAL) instead of SPA at large scaleSEAL on Qwen2.5-7B · SQuAD (120M tokens)QA accuracy (%): 91.27 -> 74.23Hurt
RL-based generator training (SEAL) reduces diversity of synthetic dataSEAL · SQuAD diversityCompression Ratio: 4.3806 (SPA) vs 19.2468 (SEAL)Hurt
use multi-stage Active Reading instead of single-stage SPAActive Reading · QuALITY (455M tokens)QA accuracy (%): 57.03 -> 51.75Hurt
swap generator from GPT-4-Turbo to gpt-oss-120b for QA baseline (ablation)QA augmentation, Llama-3-8B · QuALITY (27M tokens)QA accuracy (%): 52.99 -> 47.47Hurt
use SPA instead of QA baseline with gpt-oss-120b generatorLlama-3-8B · QuALITY (27M tokens)QA accuracy (%): 47.47 -> 52.26Improved
use stronger generator GPT-4o for SPA (ablation)SPA, Llama-3-8B · QuALITY (27M tokens)QA accuracy (%): 52.26 -> 55.49Improved
use all 7 prompts instead of any single prompt (ablation)SPA · SQuAD (22M tokens)QA accuracy (%): 78.95-85.52 (single prompts) -> 87.68 (full set)Improved
include Key concepts prompt in the set (ablation)SPA · SQuAD (22M tokens)QA accuracy (%): 86.06% -> 87.68%Improved
prune prompt set to Implications and QA-ct (task-specific tuning) (ablation)SPA · SQuAD (22M tokens)QA accuracy (%): 87.68% -> 88.19%Improved
transfer SQuAD-tuned prompt subset to QuALITY (ablation)SPA · QuALITY (27M tokens)QA accuracy (%): 52.26% -> 51.51%Hurt
use SPA instead of EntiGraph or Active ReadingMeta-Llama-3-8B · MultiHop-RAG (15M tokens)QA accuracy (%): 84.44 -> 88.36Improved

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