Papers › GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

22 Mar 2023arXiv:2303.12320archive 2025-07-28

Dhaval Taunk, Lakshya Khanna, Pavan Kandru, Vasudeva Varma, Charu Sharma, Makarand Tapaswi

Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph (WG) followed by reasoning using Graph Neural Networks(GNNs). This faces two major challenges: (i) it is difficult to capture all the information from the QA in the WG, and (ii) the WG contains some irrelevant nodes from the KG. To address these, we propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA pair. We evaluate our results on OpenBookQA, CommonsenseQA and MedQA-USMLE and see that GrapeQA shows consistent improvements over its LM + KG predecessor (QA-GNN in particular) and large improvements on OpenBookQA.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Common Sense ReasoningKnowledge GraphsQuestion Answering

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning CommonsenseQA GrapeQA: PEGA Accuracy 73.5 #15 of 38 Archive leaderboard report
Question Answering MedQA GrapeQA: PEGA Accuracy 39.51 #22 of 27 Archive leaderboard report
Question Answering OpenBookQA GrapeQA: PEGA+CANP Accuracy 90 #9 of 45 Archive leaderboard report
Question Answering OpenBookQA GrapeQA: PEGA Accuracy 82 #23 of 45 Archive leaderboard report
Question Answering OpenBookQA GrapeQA: CANP Accuracy 66.2 #28 of 45 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections