Blog

ACL 2026 — Papers on Fiction, Books, Literature, and Fictional Characters

Some of us saw this coming: computer scientists are doing a lot of research on fiction and narrative.

💥 63 papers + 2 SemEval tasks out of 6,422 publications in the latest ACL Anthology.

Curated from the ACL Anthology event page for ACL 2026.

Selection: curation over keyword filtering; excluded false positives (“novel framework”, scientific “literature”, character-level tokenization) and generic persona/role-playing-agent papers unless explicitly about fictional characters.

Generated: 2026-07-15

Main conference

• Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry
• G-Cap: A Game Character Caption Generator
• What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
• Deriving Character Logic from Storyline as Codified Decision Trees
• DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing
• Iterative Dual-Model Alignment for Story Evaluation
• CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories
• EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
• Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
• LitVISTA: A Benchmark for Narrative Orchestration in Literary Text
• Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry
• Frankentext: Stitching random text fragments into long-form narratives
• EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
• StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall
• Fiction Flows: A Replication and Reinterpretation of Narrative Sequentiality
• Evaluating Visual Narrative Coherence in Story Visualization via Diversified Storylines
• If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
• PICTURE: Enhancing Theory-of-Mind in LLMs by Revealing, Not Hiding, Characters’ Lack of Knowledge
• ChatAnime: Towards User-Centered Emotional Support in LLM-based Virtual Character Chat
• GOLEMcoref: A Multilingual Coreference Dataset of Fiction
• Dark & Stormy: Modeling Humor in Sentences from the Bulwer-Lytton Fiction Contest
• Neuro-Symbolic Agentic RL for Long-Term Original Character Companionship and Interaction
• Contextual Diversity Measure (CDM) for Controllable Story Generation in LLMs
• Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach

Findings

• BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration
• Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
• Computational Narrative Understanding for Expressive Text-to-Speech
• Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
• Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI
• Poller: Are LLMs Suitable for Evaluating Poetry Understanding Task?
• From Shijing to English and German: Resources and Evaluation for LLM Translation of Early Chinese Poetry
• Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry
• Collaborative Multi-Agent Scripts Generation for Imperfect-Information Reasoning in Murder Mystery Games
• Capabilities and Evaluation Biases of LLMs in Classical Chinese Poetry Generation: A Case Study on Tang Poetry
• BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories
• From Style to Story: A Curriculum Learning Approach for Imitative Novel Generation
• Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books
• Style over Story: Measuring LLM Narrative Preferences via Structured Selection
• MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus
• Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation
• Instruction-Guided Poetry Generation in Arabic and Its Dialects
• Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation
• ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation

Workshops

• Narrative Landscape: Mapping Narrative Dispositions Across LLMs
• Beyond Prompt-Sensitive Emotion Words: Stable Embeddings for Tang Poetry Analysis
• Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with LM Rewritings
• Beyond Genre Categories: How Narrative Pattern Coherence and Spanning Distance Shape Film Success
• Fluency and Faithfulness in Human and Machine Literary Translation
• Directional Alignment and Narrative Agency in Human–LLM Co-Writing
• Tracing Thematic Change in Early English-Language Science Fiction, 1818–1930
• In Search of Lost Adventure Novels: Supervised Genre Retrieval and Corpus Refinement in Gallica
• Never Care For What They Say? Platform vs Genre Rules in Online Horror Narratives (2007–2024)
• Between Whispers and Screams: Loudness Standard Deviation as a Proxy for Explicit Content Detection in US Romance Novels
• Computational Authorship Attribution in the Children’s Tales of Oscar and Constance Wilde: The Case of “The Selfish Giant”
• Caged Birds and Cute Bookworms: Feminine Tropes and Implicit Gender Bias in LLMs
• Baselines for Detection and Classification of Discourse Presentation in English Narrative
• Capturing Classic Authorial Style in Long-Form Story Generation with GRPO Fine-Tuning
• Thiruppugazh-KG Dataset: A Manually Annotated Resource for Computational Analysis of Tamil Devotional Literature
• A Progressive Evaluation Framework for Multicultural Analysis of Story Visualization
• ReproNLP 2026: A Third Replication of the Human Evaluation of a QAG System for Children’s Storybooks
• Noise Steering for Controlled Text Generation: Arabic Educational Story Generation
• Children’s English Reading Story Generation via SFT of Compact LLMs
• Zero Shot Phonics: Constraint-Adherent Phonics Story Generation in LLMs

SemEval overviews (fiction-adjacent shared tasks)

• SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning
• SemEval-2026 Task 5: Rating Plausibility of Word Senses in Ambiguous Stories through Narrative Understanding