LongSumEval evaluates long-document summaries via answerability and factual alignment of generated QA pairs, yielding stronger human correlation than prior metrics and enabling iterative self-improvement.
Bertscore: Evaluating text generation with bert,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Comparative study finds that tokenization choices and SSL pretraining models produce distinct effects on French ASR when assessed with linguistic and acoustic metrics beyond CER and WER.
citing papers explorer
-
LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization
LongSumEval evaluates long-document summaries via answerability and factual alignment of generated QA pairs, yielding stronger human correlation than prior metrics and enabling iterative self-improvement.
-
A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
Comparative study finds that tokenization choices and SSL pretraining models produce distinct effects on French ASR when assessed with linguistic and acoustic metrics beyond CER and WER.