Large Language Models and Book Summarization: Reading or Remembering, Which Is Better?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910048393887744 |
|---|---|
| author | Fu, Tairan Conde, Javier Reviriego, Pedro Coronado-Blázquez, Javier Melero, Nina Merino-Gómez, Elena |
| author_facet | Fu, Tairan Conde, Javier Reviriego, Pedro Coronado-Blázquez, Javier Melero, Nina Merino-Gómez, Elena |
| contents | Summarization is a core task in Natural Language Processing (NLP). Recent advances in Large Language Models (LLMs) and the introduction of large context windows reaching millions of tokens make it possible to process entire books in a single prompt. At the same time, for well-known books, LLMs can generate summaries based only on internal knowledge acquired during training. This raises several important questions: How do summaries generated from internal memory compare to those derived from the full text? Does prior knowledge influence summaries even when the model is given the book as input? In this work, we conduct an experimental evaluation of book summarization with state-of-the-art LLMs. We compare summaries of well-known books produced using (i) only the internal knowledge of the model and (ii) the full text of the book. The results show that having the full text provides more detailed summaries in general, but some books have better scores for the internal knowledge summaries. This puts into question the capabilities of models to perform summarization of long texts, as information learned during training can outperform summarization of the full text in some cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09981 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Large Language Models and Book Summarization: Reading or Remembering, Which Is Better? Fu, Tairan Conde, Javier Reviriego, Pedro Coronado-Blázquez, Javier Melero, Nina Merino-Gómez, Elena Computation and Language Summarization is a core task in Natural Language Processing (NLP). Recent advances in Large Language Models (LLMs) and the introduction of large context windows reaching millions of tokens make it possible to process entire books in a single prompt. At the same time, for well-known books, LLMs can generate summaries based only on internal knowledge acquired during training. This raises several important questions: How do summaries generated from internal memory compare to those derived from the full text? Does prior knowledge influence summaries even when the model is given the book as input? In this work, we conduct an experimental evaluation of book summarization with state-of-the-art LLMs. We compare summaries of well-known books produced using (i) only the internal knowledge of the model and (ii) the full text of the book. The results show that having the full text provides more detailed summaries in general, but some books have better scores for the internal knowledge summaries. This puts into question the capabilities of models to perform summarization of long texts, as information learned during training can outperform summarization of the full text in some cases. |
| title | Large Language Models and Book Summarization: Reading or Remembering, Which Is Better? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.09981 |