Metraipolis › archive › dc_e030e656b69d

When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation — arXiv:2608.15879

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15879
License (as archived): CC0-1.0
Archived: 2026-10-18T18:58:50.498Z
SHA-256 of the archived text: cbd7cf0c39a7b71af23612bdc5125efce08516bf85062a3439aa7031b527b99f
Stable URL of this page: https://metraipolis.com/documento/dc_e030e656b69d

How to cite

When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation — arXiv:2608.15879 — arXiv (en), https://arxiv.org/abs/2608.15879 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e030e656b69d (Metraipolis archive dc_e030e656b69d, sha256 cbd7cf0c39a7b71af23612bdc5125efce08516bf85062a3439aa7031b527b99f)

BibTeX

@misc{dce030e656b69d,
  title = {When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation — arXiv:2608.15879},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15879},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e030e656b69d; sha256 cbd7cf0c39a7b71af23612bdc5125efce08516bf85062a3439aa7031b527b99f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15879. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have shown strong performance in text generation tasks, yet their effectiveness on headline generation remains sensitive to how input context is selected and presented. In this work, we investigate Bengali news headline generation as a document-level generation task that requires effective selection and presentation of salient contextual information from long-form articles. Using Gemini-2.0-Flash, Llama-3.3-70B, and GPT-4o, we systematically study the effects of context selection, prompting strategies, and in-context learning (i.e., few-shot) on the quality of headline generation. Our experiments show that providing the full article does not necessarily improve performance; instead, using selected lead paragraphs of the article can maintain, and in some cases improve, headline generation quality. We further compare Bengali Native Prompting (BNaP) and Cross-Lingual Prompting (XLP), and examine how each interacts with context-enriched prompt templates incorporating auxiliary contextual cues. Results demonstrate that prompting strategies substantially influence generation quality: XLP often yields stronger performance, particularly when combined with contextual enrichment, but its benefits are model-dependent. Additionally, few-shot prompting substantially improves Gemini, with most of the gain obtained from a single demonstration, whereas Llama shows limited benefit from additional examples. Overall, our findings highlight that effective Bengali news headline generation depends more on context relevance and prompt design than on increasing input length, offering practical insights for multilingual and low-resource LLM applications.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.15879 — 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 2026-10-18T18:06:57.868Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).