LLM-based metrics (LLM-Coverage and ALIGN SCORE) are more reliable than ROUGE and BERTScore for political perspective summaries, and reranking plus DPO training improves both coverage and faithfulness.
In Proceedings of the 61st Annual Meet- ing of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6383–6402, Toronto, Canada
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reranking-based Generation for Unbiased Perspective Summarization
LLM-based metrics (LLM-Coverage and ALIGN SCORE) are more reliable than ROUGE and BERTScore for political perspective summaries, and reranking plus DPO training improves both coverage and faithfulness.