Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.10935 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918164975058944 |
|---|---|
| author | Mullick, Ankan Bose, Sombit Saha, Rounak Bhowmick, Ayan Kumar Vempaty, Aditya Dey, Prasenjit Kokku, Ravi Goyal, Pawan Ganguly, Niloy |
| author_facet | Mullick, Ankan Bose, Sombit Saha, Rounak Bhowmick, Ayan Kumar Vempaty, Aditya Dey, Prasenjit Kokku, Ravi Goyal, Pawan Ganguly, Niloy |
| contents | In this paper, we introduce Spotlight, a novel paradigm for information extraction that produces concise, engaging narratives by highlighting the most compelling aspects of a document. Unlike traditional summaries, which prioritize comprehensive coverage, spotlights selectively emphasize intriguing content to foster deeper reader engagement with the source material. We formally differentiate spotlights from related constructs and support our analysis with a detailed benchmarking study using new datasets curated for this work. To generate high-quality spotlights, we propose a two-stage approach: fine-tuning a large language model on our benchmark data, followed by alignment via Direct Preference Optimization (DPO). Our comprehensive evaluation demonstrates that the resulting model not only identifies key elements with precision but also enhances readability and boosts the engagement value of the original document. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10935 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents Mullick, Ankan Bose, Sombit Saha, Rounak Bhowmick, Ayan Kumar Vempaty, Aditya Dey, Prasenjit Kokku, Ravi Goyal, Pawan Ganguly, Niloy Computation and Language In this paper, we introduce Spotlight, a novel paradigm for information extraction that produces concise, engaging narratives by highlighting the most compelling aspects of a document. Unlike traditional summaries, which prioritize comprehensive coverage, spotlights selectively emphasize intriguing content to foster deeper reader engagement with the source material. We formally differentiate spotlights from related constructs and support our analysis with a detailed benchmarking study using new datasets curated for this work. To generate high-quality spotlights, we propose a two-stage approach: fine-tuning a large language model on our benchmark data, followed by alignment via Direct Preference Optimization (DPO). Our comprehensive evaluation demonstrates that the resulting model not only identifies key elements with precision but also enhances readability and boosts the engagement value of the original document. |
| title | Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.10935 |