AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

PKR-QA: A Benchmark for Procedural Knowledge Reasoning with Knowledge Module Learning

Thanh-Son Nguyen, Hong Yang, Tzeh Yuan Neoh, Hao Zhang, Ee Yeo Keat, Basura Fernando

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 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
add P.VRL predicted step/task categories to VLM input (ablation)VLMs · PKR-QAaccuracy: Qwen2.5-VL 59.6 -> 69.4Improved
fine-tune VLMs on KG triplets (ablation)VLMs · PKR-QAaccuracy: Qwen2.5-VL 59.6 -> 67.3Improved
fine-tune VLMs on 1,700 QA pairs (ablation)VLMs · PKR-QAaccuracy: Qwen2.5-VL 59.6 -> 73.6Improved
add KG training on top of QA training (ablation)VLMs · PKR-QAaccuracy: Qwen2.5-VL 73.6 -> 74.2Improved
use KML-CLIP with KG+QA training instead of VLM or KG-embedding baselinesneurosymbolic methods · PKR-QAaccuracy: best VLM 74.2 -> 78.1Improved
add KG+QA training to KML-CLIP (versus KG-training only) (ablation)KML-CLIP · PKR-QAaccuracy: 75.3 -> 78.1Improved
learn KML embeddings from scratch instead of frozen CLIP (ablation)KML · PKR-QAaccuracy: KG: 74.6 -> 73.5; KG+QA: 76.7 -> 77.4Mixed
initialize KG embedding baselines with CLIP (ablation)TransE/TransH/RotatE · PKR-QAaccuracy: TransE 63.6 -> 56.8; RotatE 41.6 -> 48.8Mixed
train KML modules on PKG relations rather than QA only (ablation)KML-F-CLIP · PKR-QAmean accuracy: 59.3 -> 71.6 (accuracy KG-training)Improved
generate multiple programs instead of one (ablation)KML · PKR-QAaccuracyNo clear effect
train modules on generic WikiHow KG instead of domain PKG (ablation)KML-F-CLIP · PKR-QAmean accuracy: 74.9 (WikiHow KG+QA) vs PKG-based 75.3Hurt

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