Metraipolis › archive › dc_46583ec39bf9

TIAO: Token Importance-Aware Policy Optimization for Text Summarization — arXiv:2609.16748

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16748
License (as archived)
CC0-1.0
Archived
2026-10-15T19:19:18.424Z
SHA-256 of the archived text
16e44b57a727a38c3b840b6b272927b2733cdbc844ccf0a2475425290fd54bc5
Stable URL of this page
https://metraipolis.com/documento/dc_46583ec39bf9

How to cite

TIAO: Token Importance-Aware Policy Optimization for Text Summarization — arXiv:2609.16748 — arXiv (en), https://arxiv.org/abs/2609.16748 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46583ec39bf9 (Metraipolis archive dc_46583ec39bf9, sha256 16e44b57a727a38c3b840b6b272927b2733cdbc844ccf0a2475425290fd54bc5)
BibTeX
@misc{dc46583ec39bf9,
  title = {TIAO: Token Importance-Aware Policy Optimization for Text Summarization — arXiv:2609.16748},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16748},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46583ec39bf9; sha256 16e44b57a727a38c3b840b6b272927b2733cdbc844ccf0a2475425290fd54bc5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16748. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) have shown strong performance on this task and can be further improved through reinforcement learning (RL). However, most existing methods apply reward signals directly to undifferentiated token sequences, overlooking the varying importance of individual tokens to word and sentence level quality in summarization. In this paper, we propose Token Importance-Aware Policy Optimization (TIAO), a novel reinforcement learning strategy that explicitly leverages token-importance awareness. Specifically, TIAO identifies core tokens based on token dependency and reweights a trajectory's advantage according to its overall dependencies. Experiments on the real world dataset show that our TIAO achieves highly competitive results, and that a 7B foundation model enhanced by TIAO performs comparably to GPT-4 and GPT-5-nano. Code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.16748 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:32:32.827Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).