2026-09-20T13:35:04Zhttps://iris.unitn.it/oai/request

oai:iris.unitn.it:11572/4839522026-05-25T15:54:04Zcom_11572_237821com_11572_101871col_11572_237822ou_ou00002

Models and Application of Question Retrieval for Natural Language Processing Campese, Stefano Campese, Stefano Moschitti, Alessandro Question Retrieval, Semantic Equivalence, Database Question Answering, Question Ranking, Self-Supervised Pre-training, LLM Coherence, Retrieval-Augmented Generation, Retrieval Coherence, Dense Retrieval, Dataset Declassification, Privacy-Preserving NLP, Answer Sentence Selection This thesis investigates the role of question understanding in Question Answering systems, developing methods that exploit question semantic equivalence at progressively larger scales: from individual question pairs, through equivalence clusters, to entire datasets. The first part addresses question retrieval at scale. We introduce QUADRo, a retrieval framework operating over millions of question-answer pairs, and the Question Ranking Corpus (QRC), a large-scale resource with answer-aware annotations and challenging hard negatives. We demonstrate that incorporating answers during retrieval substantially improves accuracy, as answers serve as a semantic bridge between questions that share little lexical overlap but seek the same information. To reduce annotation costs, we develop Question Ranking Pre-training (QRP), a self-supervised method that learns question equivalence patterns without labeled data, achieving significant improvements while reducing model variance by over 50\%. The second part extends pairwise equivalence to question clusters. We analyze coherence in Large Language Models, finding that a substantial portion of question clusters exhibit incoherent behavior: models answer some phrasings correctly while failing on semantically equivalent alternatives. This reveals that understanding failures, not just knowledge gaps, limit LLM performance. We introduce Question-Augmented Generation (q-RAG), which supplements prompts with retrieved similar questions, improving accuracy by up to 9 percentage points and coherence by up to 28 points. We further show that q-RAG's benefits can be distilled into model parameters through Direct Preference Optimization (DPO) and Supervised Fine-Tuning, producing standalone models with improved coherence that surpass the inference-time approach. For retrieval systems, we apply clusters to train models for consistency: the Coherence Ranking Loss improves ranking coherence by up to 30\% while simultaneously improving relevance. The third part lifts equivalence to the dataset level. We introduce dataset declassification, a framework that replaces proprietary questions with semantically equivalent public alternatives, enabling dataset sharing without exposing sensitive content. Models trained on fully declassified data match baseline performance (WikiQA $\Delta \approx 0$, TrecQA $|\Delta| \leq 1.2$ points), and test set declassification preserves evaluation validity when high-quality mappings exist ($|\Delta| \leq 2$ on standard benchmarks), enabling the release of ``shadow benchmarks'' for evaluation integrity. We identify boundary conditions through experiments on adversarially-constructed benchmarks. Together, these contributions show that question semantic equivalence, systematically exploited at multiple scales, enables substantial improvements to QA system accuracy, consistency, and evaluation integrity. 2026-04-27 info:eu-repo/semantics/doctoralThesis https://hdl.handle.net/11572/483952 eng firstpage:1 lastpage:203 numberofpages:203 info:eu-repo/semantics/openAccess Università degli studi di Trento place:TRENTO license:Tutti i diritti riservati (All rights reserved) license uri:iris.PRI01