Knowledge-augmented question answering (QA) combines language understanding with relational evidence from knowledge graphs (KGs). QA-GNN [1] and GreaseLM [2] model language\u2013graph interactions, while DRAGON [3] learns joint representations through masked language modeling and KG link prediction.<\/p>\n\n\n\n
However, retrieved evidence can exceed practical text and graph budgets. Fixed-size inputs and sampling or truncation may discard useful relational paths, retain redundant evidence, and overlook the cost of retrieval and selection. It also remains unclear whether budget-aware evidence selection should be applied only downstream or incorporated into joint pretraining. This thesis investigates structure-preserving selection during pretraining and its impact on the end-to-end accuracy\u2013cost trade-off.<\/p>\n\n\n\n
Research Questions<\/strong><\/p>\n\n\n\n RQ1 \u2014 Evidence Selection under Budget Constraints. How can relevance, redundancy, complementarity, and structural integrity be jointly considered when selecting knowledge within text and graph budgets? Which selection principles retain decision-relevant evidence more effectively than random sampling, sequential truncation, or relevance-based ranking?<\/p>\n\n\n\n RQ2 \u2014 Selection and Joint Pretraining. Does incorporating budget-aware selection into language\u2013graph pretraining outperform compressing inputs only at the downstream stage? How do self-supervised objectives, cross-modal interaction, and training-budget settings influence the outcome?<\/p>\n\n\n\n RQ3 \u2014 Accuracy and End-to-End Cost. After accounting for retrieval, evidence selection, and model computation, can the approach attain higher accuracy at a fixed resource budget or comparable performance at lower cost? What complementary or substitutive effects arise between text and graph budgets?<\/p>\n\n\n\n RQ4 \u2014 Effective Conditions and Failure Modes. How do the benefits vary with question type, context length, knowledge coverage, and local graph structure? When does compression eliminate irrelevant information, and when does it remove essential evidence?<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" Knowledge-augmented question answering (QA) combines language understanding with relational evidence from knowledge graphs (KGs). QA-GNN [1] and GreaseLM [2] model language\u2013graph interactions, while DRAGON [3] learns joint representations through masked language modeling and KG link prediction. However, retrieved evidence can exceed practical text and graph budgets. Fixed-size inputs and sampling or truncation may discard useful […]<\/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-7493","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\/7493","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=7493"}],"version-history":[{"count":1,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7493\/revisions"}],"predecessor-version":[{"id":7494,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/7493\/revisions\/7494"}],"wp:attachment":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/media?parent=7493"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/categories?post=7493"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/tags?post=7493"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}