@inproceedings{singhania-etal-2025-recall,
title = "Recall Them All: Long List Generation from Long Novels",
author = "Singhania, Sneha and
Razniewski, Simon and
Weikum, Gerhard",
editor = "Arachchige, Isuri Nanomi and
Frontini, Francesca and
Mitkov, Ruslan and
Rayson, Paul",
booktitle = "Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.lm4dh-1.13/",
pages = "133--142",
abstract = "Language models can generate lists of salient literary characters for specific relations but struggle with long, complete lists spanning entire novels. This paper studies the non-standard setting of extracting complete entity lists from full-length books, such as identifying all 50+ friends of Harry Potter across the 7-volume book series. We construct a benchmark dataset with meticulously compiled ground-truth, posing it as a challenge for the research community. We present a first-cut method to tackle this task, based on RAG with LLMs. Our method introduces the novel contribution of harnessing IR-style pseudo-relevance feedback for effective passage retrieval from literary texts. Experimental results show that our approach clearly outperforms both LLM-only and standard RAG baselines, achieving higher recall while maintaining acceptable precision."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singhania-etal-2025-recall">
<titleInfo>
<title>Recall Them All: Long List Generation from Long Novels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sneha</namePart>
<namePart type="family">Singhania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Razniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerhard</namePart>
<namePart type="family">Weikum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isuri</namePart>
<namePart type="given">Nanomi</namePart>
<namePart type="family">Arachchige</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Frontini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language models can generate lists of salient literary characters for specific relations but struggle with long, complete lists spanning entire novels. This paper studies the non-standard setting of extracting complete entity lists from full-length books, such as identifying all 50+ friends of Harry Potter across the 7-volume book series. We construct a benchmark dataset with meticulously compiled ground-truth, posing it as a challenge for the research community. We present a first-cut method to tackle this task, based on RAG with LLMs. Our method introduces the novel contribution of harnessing IR-style pseudo-relevance feedback for effective passage retrieval from literary texts. Experimental results show that our approach clearly outperforms both LLM-only and standard RAG baselines, achieving higher recall while maintaining acceptable precision.</abstract>
<identifier type="citekey">singhania-etal-2025-recall</identifier>
<location>
<url>https://aclanthology.org/2025.lm4dh-1.13/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>133</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recall Them All: Long List Generation from Long Novels
%A Singhania, Sneha
%A Razniewski, Simon
%A Weikum, Gerhard
%Y Arachchige, Isuri Nanomi
%Y Frontini, Francesca
%Y Mitkov, Ruslan
%Y Rayson, Paul
%S Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F singhania-etal-2025-recall
%X Language models can generate lists of salient literary characters for specific relations but struggle with long, complete lists spanning entire novels. This paper studies the non-standard setting of extracting complete entity lists from full-length books, such as identifying all 50+ friends of Harry Potter across the 7-volume book series. We construct a benchmark dataset with meticulously compiled ground-truth, posing it as a challenge for the research community. We present a first-cut method to tackle this task, based on RAG with LLMs. Our method introduces the novel contribution of harnessing IR-style pseudo-relevance feedback for effective passage retrieval from literary texts. Experimental results show that our approach clearly outperforms both LLM-only and standard RAG baselines, achieving higher recall while maintaining acceptable precision.
%U https://aclanthology.org/2025.lm4dh-1.13/
%P 133-142
Markdown (Informal)
[Recall Them All: Long List Generation from Long Novels](https://aclanthology.org/2025.lm4dh-1.13/) (Singhania et al., LM4DH 2025)
ACL
- Sneha Singhania, Simon Razniewski, and Gerhard Weikum. 2025. Recall Them All: Long List Generation from Long Novels. In Proceedings of the First on Natural Language Processing and Language Models for Digital Humanities, pages 133–142, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.