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

• URL: http://arxiv.org/abs/2604.11435v1
• Date: Mon, 13 Apr 2026 13:19:56 GMT
• Title: Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books
• Abstract summary: We propose a training framework that decouples reasoning from generation.<n>Our approach 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.
• Score: 52.08691427871138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding [21.52396619311169]
  Narrative Knowledge Weaver(NKW) is a source-grounded framework that aligns textual evidence, atomic facts, canonical graph structure, entity profiles, interactions, episodes, and storylines.<n>NKW is strongest on screenplay-level story-world QA while remaining competitive on more passage-centered benchmarks.
  arXiv  Detail & Related papers  (2026-06-04T05:30:11Z)
• Learning to Reason for Long-Form Story Generation [84.09733333295338]
  We propose a general story-generation task (Next-Chapter Prediction) and a reward formulation (Verified Rewards via Completion Likelihood Improvement)<n>We learn to reason over a story's condensed information and generate a detailed plan for the next chapter.<n>Our reasoning is evaluated via the chapters it helps a story-generator create, and compared against non-trained and supervised finetuning (SFT) baselines.
  arXiv  Detail & Related papers  (2025-03-28T18:48:26Z)
• BookWorm: A Dataset for Character Description and Analysis [59.186325346763184]
  We define two tasks: character description, which generates a brief factual profile, and character analysis, which offers an in-depth interpretation. We introduce the BookWorm dataset, pairing books from the Gutenberg Project with human-written descriptions and analyses. Our findings show that retrieval-based approaches outperform hierarchical ones in both tasks.
  arXiv  Detail & Related papers  (2024-10-14T10:55:58Z)
• CHIRON: Rich Character Representations in Long-Form Narratives [98.273323001781]
  We propose CHIRON, a new character sheet' based representation that organizes and filters textual information about characters.<n>We validate CHIRON via the downstream task of masked-character prediction, where our experiments show CHIRON is better and more flexible than comparable summary-based baselines.<n> metrics derived from CHIRON can be used to automatically infer character-centricity in stories, and that these metrics align with human judgments.
  arXiv  Detail & Related papers  (2024-06-14T17:23:57Z)
• Branching Narratives: Character Decision Points Detection [13.615681132633561]
  We propose a novel dataset based on CYOA-like games graphs to be used as a benchmark for such a task. We show how such a model can be applied to the existing text to produce linear segments divided by potential branching points.
  arXiv  Detail & Related papers  (2024-05-12T13:36:07Z)
• StoryGPT-V: Large Language Models as Consistent Story Visualizers [33.68157535461168]
  generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts.<n>Yet, the emerging Large Language Model (LLM) showcases robust reasoning abilities to navigate through ambiguous references.<n>We introduce emphStoryGPT-V, which leverages the merits of the latent diffusion (LDM) and LLM to produce images with consistent and high-quality characters.
  arXiv  Detail & Related papers  (2023-12-04T18:14:29Z)
• Read before Generate! Faithful Long Form Question Answering with Machine Reading [77.17898499652306]
  Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. We propose a new end-to-end framework that jointly models answer generation and machine reading.
  arXiv  Detail & Related papers  (2022-03-01T10:41:17Z)
• LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training [76.90793623822866]
  We propose a unified framework for logical knowledge-conditioned text generation in the few-shot setting. Our approach leverages self-training and samples pseudo logical forms based on content and structure consistency.
  arXiv  Detail & Related papers  (2021-12-02T16:49:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.