Cover Image

Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bei, Beicheng, Chun, Hannah Hyesun, Guo, Chen, Saghiri, Arwa
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improving Quotation Attribution with Fictional Character Embeddings
by: Michel, Gaspard, et al.
Published: (2024)

Indexing and Visualization of Climate Change Narratives Using BERT and Causal Extraction
by: Sakaji, Hiroki, et al.
Published: (2024)

Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
by: Goel, Raghavv, et al.
Published: (2026)

Measuring Intrinsic Dimension of Token Embeddings
by: Kataiwa, Takuya, et al.
Published: (2025)

Mitigating Hallucination in Fictional Character Role-Play
by: Sadeq, Nafis, et al.
Published: (2024)

CharBench: Evaluating the Role of Tokenization in Character-Level Tasks
by: Uzan, Omri, et al.
Published: (2025)

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works
by: Yuan, Xinfeng, et al.
Published: (2024)

Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
by: Diera, Andor, et al.
Published: (2026)

Understanding Token Probability Encoding in Output Embeddings
by: Cho, Hakaze, et al.
Published: (2024)

An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
by: Nguyen, Ba-Quang
Published: (2025)

How Do Language Models Acquire Character-Level Information?
by: Sato, Soma, et al.
Published: (2026)

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
by: Xu, Zhu, et al.
Published: (2024)

Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness
by: Yang, Zhipeng, et al.
Published: (2026)

Do LLMs Encode Functional Importance of Reasoning Tokens?
by: Singh, Janvijay, et al.
Published: (2026)

Probing BERT for German Compound Semantics
by: Miletić, Filip, et al.
Published: (2025)

Adjusting Interpretable Dimensions in Embedding Space with Human Judgments
by: Erk, Katrin, et al.
Published: (2024)

Hybrid Machine Learning Model for Detecting Bangla Smishing Text Using BERT and Character-Level CNN
by: Tanbhir, Gazi, et al.
Published: (2025)

Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT
by: Banerjee, Awritrojit, et al.
Published: (2025)

Language, Interpretation, and the Art of Narrative Construction in Modern Fiction
by: -, Javeria, et al.
Published: (2025)

Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs
by: Hicke, Rebecca M. M., et al.
Published: (2025)

KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing Applications
by: Bommarito, Michael J, et al.
Published: (2025)

InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline
by: Kugler, Kai, et al.
Published: (2021)

A Causal Graph Approach to Oppositional Narrative Analysis
by: Revilla, Diego, et al.
Published: (2026)

MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation
by: Behrendt, Maike, et al.
Published: (2025)

Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters
by: Hiraoka, Tatsuya, et al.
Published: (2025)

CHIRON: Rich Character Representations in Long-Form Narratives
by: Gurung, Alexander, et al.
Published: (2024)

CHATTER: A Character Attribution Dataset for Narrative Understanding
by: Baruah, Sabyasachee, et al.
Published: (2024)

Weight Tying Biases Token Embeddings Towards the Output Space
by: Lopardo, Antonio, et al.
Published: (2026)

Few Dimensions are Enough: Fine-tuning BERT with Selected Dimensions Revealed Its Redundant Nature
by: Fukuhata, Shion, et al.
Published: (2025)

Outlier Dimensions Encode Task-Specific Knowledge
by: Rudman, William, et al.
Published: (2023)

Locations of Characters in Narratives: Andersen and Persuasion Datasets
by: Ozyurt, Batuhan, et al.
Published: (2025)

Training a Bilingual Language Model by Mapping Tokens onto a Shared Character Space
by: Rom, Aviad, et al.
Published: (2024)

iBERT: Interpretable Embeddings via Sense Decomposition
by: Anand, Vishal, et al.
Published: (2025)

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
by: Zhu, Mingkang, et al.
Published: (2025)

From Characters to Tokens: Dynamic Grouping with Hierarchical BPE
by: Dolga, Rares, et al.
Published: (2025)

Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction
by: Mtumbuka, Frank, et al.
Published: (2023)

Enriched BERT Embeddings for Scholarly Publication Classification
by: Wolff, Benjamin, et al.
Published: (2024)

Taggus: An Automated Pipeline for the Extraction of Characters' Social Networks from Portuguese Fiction Literature
by: Canário, Tiago G, et al.
Published: (2025)

Beyond Tokens: Concept-Level Training Objectives for LLMs
by: Iyer, Laya, et al.
Published: (2026)

CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations
by: Rosenberger, Julian, et al.
Published: (2025)