DoGMaTiQ automates QA-nugget creation via document-grounded generation, paraphrase clustering, and quality-based subselection, yielding strong rank correlations with human judgments on cross-lingual TREC tasks.
In Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) , pages 118–144, Mexico City, Mexico
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
A systematic survey that analyzes 134 papers, proposes a unified taxonomy for evidence-based LLM text generation, and examines 300 evaluation metrics across seven dimensions.
citing papers explorer
-
DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation
DoGMaTiQ automates QA-nugget creation via document-grounded generation, paraphrase clustering, and quality-based subselection, yielding strong rank correlations with human judgments on cross-lingual TREC tasks.
-
Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
A systematic survey that analyzes 134 papers, proposes a unified taxonomy for evidence-based LLM text generation, and examines 300 evaluation metrics across seven dimensions.