Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Papoudakis, Argyrios, Lapata, Mirella, Keller, Frank
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913030782058496
author Papoudakis, Argyrios
Lapata, Mirella
Keller, Frank
author_facet Papoudakis, Argyrios
Lapata, Mirella
Keller, Frank
contents Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-driven simulations. However, generating accurate character descriptions from long-form narratives (e.g., novels) is challenging: models must track evolving attributes (e.g., relationships and events), integrate evidence scattered across the text, and infer implicit details. Despite the success of reasoning-enabled LLMs on many benchmarks, we find that for character description generation their performance improves when built-in reasoning is disabled (i.e., an empty reasoning trace). Motivated by this, we propose a training framework that decouples reasoning from generation. Our approach, which can be applied on top of long-context LLMs or chunk-based methods, consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description. Experiments on two datasets (BookWorm and CroSS) show that QA-guided reasoning improves faithfulness, informativeness, and grounding over strong long-context baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11435
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books
Papoudakis, Argyrios
Lapata, Mirella
Keller, Frank
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-driven simulations. However, generating accurate character descriptions from long-form narratives (e.g., novels) is challenging: models must track evolving attributes (e.g., relationships and events), integrate evidence scattered across the text, and infer implicit details. Despite the success of reasoning-enabled LLMs on many benchmarks, we find that for character description generation their performance improves when built-in reasoning is disabled (i.e., an empty reasoning trace). Motivated by this, we propose a training framework that decouples reasoning from generation. Our approach, which can be applied on top of long-context LLMs or chunk-based methods, consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description. Experiments on two datasets (BookWorm and CroSS) show that QA-guided reasoning improves faithfulness, informativeness, and grounding over strong long-context baselines.
title Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2604.11435