QA-GNN [1] and GreaseLM [2] combine textual context with knowledge graph evidence for QA, while DRAGON [3] pretrains joint language\u2013graph representations. ConceptNet [5] provides structured commonsense knowledge, and choice-based decision interfaces such as Jev [4] motivate candidate-defined answer spaces.<\/p>\n\n\n\n
Yet joint representation pretraining does not directly establish a reusable candidate-decision function. In particular, it remains unclear how KG relations can provide downstream-task-agnostic decision supervision, whether one model can generalize to previously unseen QA tasks and varying numbers of candidates, and whether its decision probabilities remain reliable. This thesis studies ConceptNet-specific pretraining without target-QA-task supervision, using shared candidate scoring to support transferable decision making.<\/p>\n\n\n\n
Research Questions<\/p>\n\n\n\n
RQ1 \u2014 Knowledge-Driven Decision Learning.How can ConceptNet relations and local structures support task-agnostic decision-pretraining objectives that teach a model to evaluate candidate answers using knowledge evidence? Relative to language-only training and generic self-supervised language\u2013graph pretraining, what produces the observed gains?<\/p>\n\n\n\n
RQ2 \u2014 Transfer across QA Tasks. Can one pretrained decision model be applied to different commonsense QA tasks without using target-task labels? How is transfer affected by question format, knowledge coverage, and reasoning requirements, and what improvements arise from limited labeled adaptation?<\/p>\n\n\n\n
RQ3 \u2014 Generalization across Candidate Sets.<\/strong> Can the model preserve meaningful semantic decisions when the number of options, distractor difficulty, or answer wording changes? How can architectural support for variable-sized option sets be distinguished from empirical generalization to previously unseen candidate sets?<\/p>\n\n\n\n
RQ4 \u2014 Reliability of Decision Probabilities. Do predicted probabilities reflect actual reliability when answer-option sets and supporting knowledge change? Can task-agnostic training and calibration mitigate overconfidence during cross-task deployment?<\/p>\n\n\n\n
<\/p>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
QA-GNN [1] and GreaseLM [2] combine textual context with knowledge graph evidence for QA, while DRAGON [3] pretrains joint language\u2013graph representations. ConceptNet [5] provides structured commonsense knowledge, and choice-based decision interfaces such as Jev [4] motivate candidate-defined answer spaces. Yet joint representation pretraining does not directly establish a reusable candidate-decision function. In particular, it remains […]<\/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":[90,87,46],"class_list":["post-7491","post","type-post","status-publish","format-standard","hentry","category-thesis","tag-attention-residuals","tag-commonsense-qa","tag-llm"],"acf":[],"_links":{"self":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7491","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=7491"}],"version-history":[{"count":1,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7491\/revisions"}],"predecessor-version":[{"id":7492,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7491\/revisions\/7492"}],"wp:attachment":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/media?parent=7491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/categories?post=7491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/tags?post=7491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}