Text-to-Stage: Spatial Layouts from Long-form Narratives

• URL: http://arxiv.org/abs/2603.17832v1
• Date: Wed, 18 Mar 2026 15:26:27 GMT
• Title: Text-to-Stage: Spatial Layouts from Long-form Narratives
• Abstract summary: We probe the ability of a language model to demonstrate spatial reasoning from unstructured text.<n>We introduce a dramaturgy-inspired deterministic evaluation suite and a training and inference recipe.<n>Experiments on a text-only corpus of classical English literature demonstrate improvements over vanilla models.
• Score: 26.910880317766384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications. Concretely, we study the narrative-to-play task: inferring stage-play layouts (scenes, speaker positions, movements, and room types) from text that lacks explicit spatial, positional, or relational cues. We then introduce a dramaturgy-inspired deterministic evaluation suite and, finally, a training and inference recipe that combines rejection SFT using Best-of-N sampling with RL from verifiable rewards via GRPO. Experiments on a text-only corpus of classical English literature demonstrate improvements over vanilla models across multiple metrics (character attribution, spatial plausibility, and movement economy), as well as alignment with an LLM-as-a-judge and subjective human preferences.

Related papers

• LitVISTA: A Benchmark for Narrative Orchestration in Literary Text [20.35180998049897]
  Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts.<n>Existing large language models can generate long stories but overly focus on causal coherence.<n>We propose VISTA Space, a high-dimensional representational framework for narrative orchestration.
  arXiv  Detail & Related papers  (2026-01-10T06:08:28Z)
• SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space [11.534994345027362]
  Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation.<n>We introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance.<n>We introduce SPARTA-a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder.
  arXiv  Detail & Related papers  (2025-10-28T14:09:05Z)
• Classifying Unreliable Narrators with Large Language Models [23.817691955577835]
  We present TUNa, a human-annotated dataset of narratives from multiple domains.<n>We define classification tasks for intra-narrational, inter-narrational, and inter-textual unreliabilities.<n>We propose learning from literature to perform unreliable narrator classification on real-world text data.
  arXiv  Detail & Related papers  (2025-06-11T23:17:12Z)
• A Personalized Conversational Benchmark: Towards Simulating Personalized Conversations [112.81207927088117]
  PersonaConvBench is a benchmark for evaluating personalized reasoning and generation in multi-turn conversations with large language models (LLMs)<n>We benchmark several commercial and open-source LLMs under a unified prompting setup and observe that incorporating personalized history yields substantial performance improvements.
  arXiv  Detail & Related papers  (2025-05-20T09:13:22Z)
• Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction [50.630431647192054]
  This paper investigates a novel approach for Target Speech Extraction (TSE)<n>It relies solely on textual context to extract the target speech.<n>We present three CSE models and analyze their performances on three datasets.
  arXiv  Detail & Related papers  (2025-03-11T18:26:10Z)
• Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs [50.0874045899661]
  We introduce CharacterBot, a model designed to replicate both the linguistic patterns and distinctive thought patterns as manifested in the textual works of a character.<n>Using Lu Xun, a renowned Chinese writer as a case study, we propose four training tasks derived from his 17 essay collections.<n>These include a pre-training task focused on mastering external linguistic structures and knowledge, as well as three fine-tuning tasks.<n>We evaluate CharacterBot on three tasks for linguistic accuracy and opinion comprehension, demonstrating that it significantly outperforms the baselines on our adapted metrics.
  arXiv  Detail & Related papers  (2025-02-18T16:11:54Z)
• Towards Aligning Language Models with Textual Feedback [43.55450701925131]
  ALT (ALignment with Textual feedback) is an approach that aligns language models with user preferences expressed in text.<n>We explore the efficacy and efficiency of textual feedback across different tasks such as toxicity reduction, summarization, and dialog response generation.
  arXiv  Detail & Related papers  (2024-07-24T03:32:05Z)
• PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer [16.07576878783396]
  We introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles. We propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts.
  arXiv  Detail & Related papers  (2023-11-14T18:50:51Z)
• PerPLM: Personalized Fine-tuning of Pretrained Language Models via Writer-specific Intermediate Learning and Prompts [16.59511985633798]
  Pretrained language models (PLMs) are powerful tools for capturing context. PLMs are typically pretrained and fine-tuned for universal use across different writers. This study aims to improve the accuracy of text understanding tasks by personalizing the fine-tuning of PLMs for specific writers.
  arXiv  Detail & Related papers  (2023-09-14T14:03:48Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance [55.10864476206503]
  We investigate the use of quantized vectors to model the latent linguistic embedding. By enforcing different policies over the latent spaces in the training, we are able to obtain a latent linguistic embedding. Our experiments show that the voice cloning system built with vector quantization has only a small degradation in terms of perceptive evaluations.
  arXiv  Detail & Related papers  (2021-06-25T07:51:35Z)
• Abstractive Summarization of Spoken and Written Instructions with BERT [66.14755043607776]
  We present the first application of the BERTSum model to conversational language. We generate abstractive summaries of narrated instructional videos across a wide variety of topics. We envision this integrated as a feature in intelligent virtual assistants, enabling them to summarize both written and spoken instructional content upon request.
  arXiv  Detail & Related papers  (2020-08-21T20:59:34Z)

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.