Imagen de Portada

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Valois, Pedro H. V., Souza, Lincon S., Shimomoto, Erica K., Fukui, Kazuhiro
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Punchlines to Predictions: A Metric to Assess LLM Performance in Identifying Humor in Stand-Up Comedy
por: Romanowski, Adrianna, et al.
Publicado: (2025)

Second-order difference subspace
por: Fukui, Kazuhiro, et al.
Publicado: (2024)

Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
por: Valois, Pedro, et al.
Publicado: (2023)

Hype or not? Formalizing Automatic Promotional Language Detection in Biomedical Research
por: Batalo, Bojan, et al.
Publicado: (2025)

Multilingual Definition Modeling
por: Marrese-Taylor, Edison, et al.
Publicado: (2025)

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
por: R V, Kavin, et al.
Publicado: (2025)

Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck
por: Ludan, Josh Magnus, et al.
Publicado: (2023)

HyPerAlign: Interpretable Personalized LLM Alignment via Hypothesis Generation
por: Garbacea, Cristina, et al.
Publicado: (2025)

Token Prediction as Implicit Classification to Identify LLM-Generated Text
por: Chen, Yutian, et al.
Publicado: (2023)

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
por: Lee, Sunbowen, et al.
Publicado: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness
por: Ma, Shixuan, et al.
Publicado: (2024)

Text2Token: Unsupervised Text Representation Learning with Token Target Prediction
por: An, Ruize, et al.
Publicado: (2025)

Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation
por: Liu, Xiaozhao, et al.
Publicado: (2025)

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
por: Kumbhar, Shrinidhi, et al.
Publicado: (2025)

Creating Targeted, Interpretable Topic Models with LLM-Generated Text Augmentation
por: Lieb, Anna, et al.
Publicado: (2025)

The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive
por: Bogdan, Alex, et al.
Publicado: (2026)

Rep2Text: Decoding Full Text from a Single LLM Token Representation
por: Zhao, Haiyan, et al.
Publicado: (2025)

Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
por: Fukui, Hiroki
Publicado: (2026)

Concept Based Continuous Prompts for Interpretable Text Classification
por: Chen, Qian, et al.
Publicado: (2024)

Linearly-Interpretable Concept Embedding Models for Text Analysis
por: De Santis, Francesco, et al.
Publicado: (2024)

Scaling Concept With Text-Guided Diffusion Models
por: Huang, Chao, et al.
Publicado: (2024)

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines
por: Gao, Jiechao, et al.
Publicado: (2026)

Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection
por: Wu, Chenwang, et al.
Publicado: (2026)

Multi-LLM Text Summarization
por: Fang, Jiangnan, et al.
Publicado: (2024)

Enhancing Medication Recommendation with LLM Text Representation
por: Lee, Yu-Tzu
Publicado: (2024)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
por: Kim, Eunji, et al.
Publicado: (2024)

LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText
por: Marturi, Krishna Chaitanya, et al.
Publicado: (2025)

Representation-Guided Parameter-Efficient LLM Unlearning
por: Xiao, Zeguan, et al.
Publicado: (2026)

Vector Arithmetic in Concept and Token Subspaces
por: Feucht, Sheridan, et al.
Publicado: (2025)

LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations
por: Wang, Yile, et al.
Publicado: (2025)

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
por: Qiao, Hezhe, et al.
Publicado: (2026)

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
por: Shabalin, Alexander, et al.
Publicado: (2025)

The Cylindrical Representation Hypothesis for Language Model Steering
por: Gao, Lang, et al.
Publicado: (2026)

Expert-Guided Extinction of Toxic Tokens for Debiased Generation
por: Sun, Xueyao, et al.
Publicado: (2024)

Enhancing Interpretable Image Classification Through LLM Agents and Conditional Concept Bottleneck Models
por: Jiang, Yiwen, et al.
Publicado: (2025)

Token-Level Marginalization for Multi-Label LLM Classifiers
por: Praharaj, Anjaneya, et al.
Publicado: (2025)

Training-free LLM-generated Text Detection by Mining Token Probability Sequences
por: Xu, Yihuai, et al.
Publicado: (2024)

Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens
por: Kashiwagi, Yosuke, et al.
Publicado: (2024)

RepEval: Effective Text Evaluation with LLM Representation
por: Sheng, Shuqian, et al.
Publicado: (2024)