@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://preview.aclanthology.org/cawl-year/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}."
}