@inproceedings{iyer-caragea-2026-bloop,
title = "{BL}oo{P}: Zero-Shot Abstractive Summarization Using Large Language Models with Bigram Lookahead Promotion",
author = "Iyer, Varun and
Caragea, Cornelia",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.482/",
doi = "10.63317/53bjejyjyh8r",
pages = "6080--6102",
abstract = "Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP (Bigram Lookahead Promotion), a simple training-free decoding intervention that encourages large language models (LLMs) to generate tokens that form bigrams from the source document. BLooP operates through a hash table lookup at each decoding step, requiring no training, fine-tuning, or model modification. We demonstrate improvements in ROUGE and BARTScore for \href{https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct}{Llama-3.1-8B-Instruct}, \href{https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407}{Mistral-Nemo-Instruct-2407}, and \href{https://huggingface.co/google/gemma-2-9b-it}{Gemma-2-9B-IT} on CNN/DM, CCSum, Multi-News, and SciTLDR. Human evaluation shows that BLooP significantly improves faithfulness without reducing readability. We make the code available \href{https://github.com/varuniyer/BLooP}{here}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iyer-caragea-2026-bloop">
<titleInfo>
<title>BLooP: Zero-Shot Abstractive Summarization Using Large Language Models with Bigram Lookahead Promotion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP (Bigram Lookahead Promotion), a simple training-free decoding intervention that encourages large language models (LLMs) to generate tokens that form bigrams from the source document. BLooP operates through a hash table lookup at each decoding step, requiring no training, fine-tuning, or model modification. We demonstrate improvements in ROUGE and BARTScore for \hrefhttps://huggingface.co/meta-llama/Llama-3.1-8B-InstructLlama-3.1-8B-Instruct, \hrefhttps://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407Mistral-Nemo-Instruct-2407, and \hrefhttps://huggingface.co/google/gemma-2-9b-itGemma-2-9B-IT on CNN/DM, CCSum, Multi-News, and SciTLDR. Human evaluation shows that BLooP significantly improves faithfulness without reducing readability. We make the code available \hrefhttps://github.com/varuniyer/BLooPhere.</abstract>
<identifier type="citekey">iyer-caragea-2026-bloop</identifier>
<identifier type="doi">10.63317/53bjejyjyh8r</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.482/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6080</start>
<end>6102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLooP: Zero-Shot Abstractive Summarization Using Large Language Models with Bigram Lookahead Promotion
%A Iyer, Varun
%A Caragea, Cornelia
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F iyer-caragea-2026-bloop
%X Abstractive summarization requires models to generate summaries that convey information in the source document. While large language models can generate summaries without fine-tuning, they often miss key details and include extraneous information. We propose BLooP (Bigram Lookahead Promotion), a simple training-free decoding intervention that encourages large language models (LLMs) to generate tokens that form bigrams from the source document. BLooP operates through a hash table lookup at each decoding step, requiring no training, fine-tuning, or model modification. We demonstrate improvements in ROUGE and BARTScore for \hrefhttps://huggingface.co/meta-llama/Llama-3.1-8B-InstructLlama-3.1-8B-Instruct, \hrefhttps://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407Mistral-Nemo-Instruct-2407, and \hrefhttps://huggingface.co/google/gemma-2-9b-itGemma-2-9B-IT on CNN/DM, CCSum, Multi-News, and SciTLDR. Human evaluation shows that BLooP significantly improves faithfulness without reducing readability. We make the code available \hrefhttps://github.com/varuniyer/BLooPhere.
%R 10.63317/53bjejyjyh8r
%U https://aclanthology.org/2026.lrec-1.482/
%U https://doi.org/10.63317/53bjejyjyh8r
%P 6080-6102
Markdown (Informal)
[BLooP: Zero-Shot Abstractive Summarization Using Large Language Models with Bigram Lookahead Promotion](https://aclanthology.org/2026.lrec-1.482/) (Iyer & Caragea, LREC 2026)
ACL