AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

GNN is a Counter? Revisiting GNN for Question Answering

Kuan Wang, Yuyu Zhang, Diyi Yang, Le Song, Tao Qin

ICLR 2022 · Large language models › Retrieval and knowledge · approach: Explanatory and multiple-choice QA benchmarks · 12 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
replace complex graph reasoning with Graph Soft CounterRoBERTa-large QA with ConceptNet · CommonsenseQA IHdevaccuracy: 76.54~($\pm$0.21) -> 79.11~($\pm$0.22)Improved
replace complex graph reasoning with Graph Soft CounterRoBERTa-large QA with ConceptNet · CommonsenseQA IHtestaccuracy: 73.41~($\pm$0.92) -> 74.48~($\pm$0.41)Improved
replace complex graph reasoning with Graph Soft CounterRoBERTa-large QA with ConceptNet · OpenBookQA testaccuracy: 67.80\footnotemark~($\pm$2.75) -> 70.33~($\pm$0.81)Improved
replace complex graph reasoning with Graph Soft CounterAristoRoBERTa QA with ConceptNet · OpenBookQA testaccuracy: 82.77~($\pm$1.56) -> 86.67~($\pm$0.46)Improved
use hard 2-hop edge counts with a two-layer MLP instead of soft graph counting (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 74.13~($\pm$0.08)No clear effect
use hard 1-hop edge counts with a two-layer MLP instead of soft graph counting (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 73.62~($\pm$0.12)Hurt
increase retrieved-node cap from QA-context entities to 32 (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 74.40~($\pm$0.25)No clear effect
increase retrieved-node cap from QA-context entities to 64 (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 73.93~($\pm$1.09)Hurt
increase retrieved-node cap from QA-context entities to 128 (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 72.78~($\pm$1.15)Hurt
increase retrieved-node cap from QA-context entities to 256 (ablation)GSC on CommonsenseQA · CommonsenseQA IHtestaccuracy: 74.48~($\pm$0.41) -> 73.89~($\pm$0.63)Hurt
apply SparseVD pruning during training (ablation)KagNet · CommonsenseQA IHtestaccuracy: 69.01~($\pm$0.76) -> 70.48~($\pm$0.77)Improved
apply SparseVD pruning during training (ablation)MHGRN · CommonsenseQA IHtestaccuracy: 71.11~($\pm$0.81) -> 72.66~($\pm$0.61)Improved

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