@inproceedings{mullick-etal-2025-introducing,
title = "Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents",
author = "Mullick, Ankan and
Bose, Sombit and
Saha, Rounak and
Bhowmick, Ayan Kumar and
Vempaty, Aditya and
Dey, Prasenjit and
Kokku, Ravi and
Goyal, Pawan and
Ganguly, Niloy",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1796/",
pages = "35449--35477",
ISBN = "979-8-89176-332-6",
abstract = "Analyzing and processing vast amounts of textual data presents significant challenges in efficiently extracting key information.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 highlights (fragmented key points) and 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. Datasets and code are available at https://github.com/ankan2/Spotlight-EMNLP2025."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mullick-etal-2025-introducing">
<titleInfo>
<title>Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankan</namePart>
<namePart type="family">Mullick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sombit</namePart>
<namePart type="family">Bose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rounak</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayan</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Bhowmick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Vempaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasenjit</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravi</namePart>
<namePart type="family">Kokku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Analyzing and processing vast amounts of textual data presents significant challenges in efficiently extracting key information.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 highlights (fragmented key points) and 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. Datasets and code are available at https://github.com/ankan2/Spotlight-EMNLP2025.</abstract>
<identifier type="citekey">mullick-etal-2025-introducing</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1796/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>35449</start>
<end>35477</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents
%A Mullick, Ankan
%A Bose, Sombit
%A Saha, Rounak
%A Bhowmick, Ayan Kumar
%A Vempaty, Aditya
%A Dey, Prasenjit
%A Kokku, Ravi
%A Goyal, Pawan
%A Ganguly, Niloy
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F mullick-etal-2025-introducing
%X Analyzing and processing vast amounts of textual data presents significant challenges in efficiently extracting key information.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 highlights (fragmented key points) and 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. Datasets and code are available at https://github.com/ankan2/Spotlight-EMNLP2025.
%U https://aclanthology.org/2025.emnlp-main.1796/
%P 35449-35477
Markdown (Informal)
[Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents](https://aclanthology.org/2025.emnlp-main.1796/) (Mullick et al., EMNLP 2025)
ACL
- Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Aditya Vempaty, Prasenjit Dey, Ravi Kokku, Pawan Goyal, and Niloy Ganguly. 2025. Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 35449–35477, Suzhou, China. Association for Computational Linguistics.