AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models

Xiaoman Pan, Wenlin Yao, Hongming Zhang, Dian Yu, Dong Yu, Jianshu Chen

ICLR 2023 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 2 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
Add KiC's instance-adaptive knowledge-rich memory and selectorT5-LM-adapt Large · MMLU test averageaccuracy: 31.8 -> 39.4Improved
Replace English Wikipedia plain-text memory with knowledge-rich memory (ablation)KiC Large · MMLU test averageaccuracy: 33.5 -> 39.4Improved
Add a knowledge selector that routes instances to a selected knowledge category (ablation)KiC Large · MMLU test averageaccuracy: 37.4 -> 39.4Improved
Use an instance-adaptive selector instead of a task-adaptive selector (ablation)KiC Large · MMLU test averageaccuracy: 36.7 -> 39.4Improved
Add a generalist expert that can skip external knowledge (ablation)KiC Large · MMLU test averageaccuracy: 38.5 -> 39.4Improved
Add external knowledge (ablation)KiC Large · P3 held-out tasks averagemedian accuracy: 51.2 -> 57.6Improved
Use knowledge-rich memory instead of English Wikipedia plain text (ablation)KiC Large · P3 held-out tasks averagemedian accuracy: 53.3 -> 57.6Improved
Add a knowledge selector rather than retrieving from all categories together (ablation)KiC Large · P3 held-out tasks averagemedian accuracy: 53.9 -> 57.6Improved
Use instance-adaptive rather than task-adaptive knowledge selection (ablation)KiC Large · P3 held-out tasks averagemedian accuracy: 55.1 -> 57.6Improved
Add a generalist expert that can skip external knowledge (ablation)KiC Large · P3 held-out tasks averagemedian accuracy: 56.6 -> 57.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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