AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Multiple Streams of Knowledge Retrieval: Enriching and Recalling in Transformers

Todd Nief, David Reber, Sean M. Richardson, Ari Holtzman

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs

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
add the output projection O matrix to FFN grafting at the final token (ablation)component grafting, Gemma · Relation completion headline testtop-5 accuracy: removing the O matrix and only using the FFN harms top-5 accuracy by 29%Improved
add the output projection O matrix to FFN grafting at the final token (ablation)component grafting, Llama3 · Relation completion headline testtop-5 accuracy: removing the O matrix and only using the FFN harms top-5 accuracy by 41%Improved
graft task ATTN at first entity in hybrid model (ablation)hybrid grafting of Gemma and Llama3 · Relation completion headline testtop-5 accuracy: 63% top-5 accuracy for Gemma and 34% for Llama3Improved
graft task FFNs at first entity instead of task ATTN (ablation)hybrid grafting · Relation completion headline testtop-5 accuracyNo clear effect
graft both FFN up and down projections together with O matrix rather than either alone (ablation)component grafting at final token · Relation completion headline testtop-5 accuracyImproved
graft the complement of first entity and last token positions (ablation)position grafting, all models · Relation completion headline testtop-5 accuracy: near-zero top-5 accuracy, comparable to pretrained modelHurt
add movie title to last token grafting (ablation)position grafting · Relation completion with movie title in test sentencetop-5 accuracyImproved
add movie title to first entity grafting (ablation)position grafting · Relation completion with movie title in test sentencetop-5 accuracyMixed
use finetuned instead of pretrained unembeddings (ablation)position grafting · Relation completion headline testtop-5 accuracyNo clear effect
use less aggressive finetuning (lower learning rate, no weight decay, supplemental data) (ablation)Gemma position grafting · Relation completion headline testtop-5 accuracyHurt

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