Answers are grounded in this paper and cite their sources.
Experiments demonstrate high scores in generating summaries for trade news, indicating effective summarization techniques.
We present TradeNewsSum—a corpus for abstractive summarization of international trade news—covering Russian- and English-language publications from domain-specific sources. All summaries are manually prepared following unified guidelines. We conducted experiments with fine-tuning transformer and seq2seq models and performed automatic evaluation using the LLM-as-a-judge scheme. LLaMA 3.1 in instruction-prompting mode achieved the best results, showing high scores across metrics, including factual completeness.
No takes yet. Share an insight, caveat, or question.
Liutova et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: