{"id":6961,"date":"2026-03-02T17:42:51","date_gmt":"2026-03-02T16:42:51","guid":{"rendered":"https:\/\/dbis.rwth-aachen.de\/dbis\/?p=6961"},"modified":"2026-03-03T13:52:40","modified_gmt":"2026-03-03T12:52:40","slug":"from-triples-to-pixels-visual-knowledge-graph-encoding-for-knowledge-augmented-multiple-choice-question-answering","status":"publish","type":"post","link":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/2026\/from-triples-to-pixels-visual-knowledge-graph-encoding-for-knowledge-augmented-multiple-choice-question-answering\/","title":{"rendered":"From Triples to Pixels: Visual Knowledge Graph Encoding for Knowledge-Augmented Multiple-Choice Question Answering"},"content":{"rendered":"\n<p>Knowledge-augmented multiple-choice question answering (MCQA) aims to improve robustness and factual grounding by integrating external structured knowledge (e.g., knowledge graphs) into language-model-based decision making. Current high-performing systems typically retrieve a local subgraph relevant to a question and candidate answers, then combine pretrained language representations with explicit graph reasoning modules.<\/p>\n\n\n\n<p>This thesis investigates an alternative representation path: instead of processing retrieved knowledge graph (KG) subgraphs as symbolic triples with graph neural networks, the subgraphs are deterministically rendered into a compact 2D \u201cvisual graph\u201d representation and encoded with a vision backbone. The resulting visual KG evidence is fused with a encoder-only language model via attention-based cross-modal interaction. The core research question is whether a visually encoded KG can preserve decision-relevant relational structure and support competitive knowledge-augmented MCQA performance on CommonsenseQA and OpenBookQA (optionally extending to MedQA-USMLE).<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Knowledge-augmented multiple-choice question answering (MCQA) aims to improve robustness and factual grounding by integrating external structured knowledge (e.g., knowledge graphs) into language-model-based decision making. Current high-performing systems typically retrieve a local subgraph relevant to a question and candidate answers, then combine pretrained language representations with explicit graph reasoning modules. This thesis investigates an alternative representation [&hellip;]<\/p>\n","protected":false},"author":145,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[21],"tags":[87,46,82],"class_list":["post-6961","post","type-post","status-publish","format-standard","hentry","category-thesis","tag-commonsense-qa","tag-llm","tag-vlm"],"acf":[],"_links":{"self":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6961","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/users\/145"}],"replies":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/comments?post=6961"}],"version-history":[{"count":1,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6961\/revisions"}],"predecessor-version":[{"id":6962,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6961\/revisions\/6962"}],"wp:attachment":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/media?parent=6961"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/categories?post=6961"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/tags?post=6961"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}