AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Knowledge Fusion of Large Language Models via Modular SkillPacks

Guodong DU, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi, Wanyu Lin, Ho-Kin Tang, Xiucheng Li, Fangming Liu, Wenya Wang, Min Zhang, Jing Li

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 14 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
use SVD instead of pruning for MLP module compression (ablation)GraftLLM · MATH (~5% compression)accuracy: 70.2 -> 72.1Improved
use SVD instead of no compression strategy (Null) on MLP modules (ablation)GraftLLM · MATH (~5% compression)accuracy: 68.7 -> 72.1Improved
add mixed-precision quantization (ablation)GraftLLM MLP modules · MATH (~5% compression)accuracy: 71.5 -> 72.1Improved
add quantization at all (ablation)GraftLLM MLP modules · MATH (~5% compression)accuracy: 69.2 -> 72.1Improved
use low-rank SVD for attention modules (ablation)GraftLLM · MATH (~5% compression)accuracy: 71.2 (pruning) -> 72.1Improved
use pruning for embedding and output head (ablation)GraftLLM · MATH (~5% compression)accuracy: 71.7 (low-rank SVD) -> 72.1No clear effect
ensemble top-2 SkillPacks instead of top-1 (ablation)Routed GraftLLM · AlpacaEval 2.0 (explicit fusion)Win Rate (%): 16.56 -> 17.33 (2.03x inference cost)Improved
ensemble top-2 SkillPacks instead of top-1 (ablation)Routed GraftLLM · Finance+Law+Bio fusionAverage score: 49.62 -> 49.64No clear effect
ensemble top-3 SkillPacks instead of top-1 (ablation)Routed GraftLLM · Implicit fusion avg of 10 benchmarksAverage score: 56.0 -> 56.4No clear effect
graft SkillPack with routing instead of parameter merging/routed LoRAOpenChat-3.5-7B explicit fusion · AlpacaEval 2.0 (explicit fusion)LC Win Rate (%): 24.81 -> 25.42 vs Twin-Merging r1024Improved
use SkillPack instead of model grafting/Model TailorLlama-3.1-8B-Instruct forget-free learning · code then math averageAverage score: 62.2 -> 64.3Improved
use GraftLLM instead of FuseChat-3 on instruction followingLlama-3.1-8B-Instruct implicit fusion · MT-Bench / AlpacaEval-2 LCscore: 9.0 -> 8.8 MT-Bench; 65.4 -> 64.8 LCHurt

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