Imagen de Portada

LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mazurets, Olexander, Barmak, Olexander, Bedratyuk, Leonid, Krak, Iurii
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing
por: Bedratyuk, Leonid
Publicado: (2026)

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
por: Kang, Minki, et al.
Publicado: (2024)

How Large Language Models are Transforming Machine-Paraphrased Plagiarism
por: Wahle, Jan Philip, et al.
Publicado: (2022)

PANER: A Paraphrase-Augmented Framework for Low-Resource Named Entity Recognition
por: Rengarajan, Nanda Kumar, et al.
Publicado: (2025)

AdParaphrase: Paraphrase Dataset for Analyzing Linguistic Features toward Generating Attractive Ad Texts
por: Murakami, Soichiro, et al.
Publicado: (2025)

Detecting AI-Generated Paraphrases in Bengali: A Comparative Study of Zero-Shot and Fine-Tuned Transformers
por: Islam, Md. Rakibul, et al.
Publicado: (2025)

LAG: Logic-Augmented Generation from a Cartesian Perspective
por: Xiao, Yilin, et al.
Publicado: (2025)

Action Controlled Paraphrasing
por: Shi, Ning, et al.
Publicado: (2024)

Language Modeling and Understanding Through Paraphrase Generation and Detection
por: Wahle, Jan Philip
Publicado: (2026)

Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
por: Bae, Jeongin, et al.
Publicado: (2026)

Multi-Scale Manifold Alignment for Interpreting Large Language Models: A Unified Information-Geometric Framework
por: Zhang, Yukun, et al.
Publicado: (2025)

Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?
por: Gogoulou, Evangelia, et al.
Publicado: (2025)

Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks
por: Idrissi, Badr Youbi, et al.
Publicado: (2025)

Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
por: Li, Yafu, et al.
Publicado: (2024)

Enhanced Sentiment Interpretation via a Lexicon-Fuzzy-Transformer Framework
por: Rokhva, Shayan, et al.
Publicado: (2025)

Integration of Contextual Descriptors in Ontology Alignment for Enrichment of Semantic Correspondence
por: Manziuk, Eduard, et al.
Publicado: (2024)

PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks
por: Zha, Yiwei, et al.
Publicado: (2025)

CoPaGE-300K: Controlled Paraphrase Geometry Embeddings
por: Bedratyuk, Leonid
Publicado: (2026)

Kantian-Utilitarian XAI: Meta-Explained
por: Atf, Zahra, et al.
Publicado: (2025)

A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
por: Mamalakis, Michail, et al.
Publicado: (2026)

Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
por: Bianco, Pedro Dal, et al.
Publicado: (2026)

ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer
por: Horvitz, Zachary, et al.
Publicado: (2023)

WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization
por: Gevers, Ine, et al.
Publicado: (2025)

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer
por: Kaneko, Masahiro
Publicado: (2026)

Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning
por: Som, Anirudh, et al.
Publicado: (2023)

Training With "Paraphrasing the Original Text" Teaches LLM to Better Retrieve in Long-context Tasks
por: Yu, Yijiong, et al.
Publicado: (2023)

Paraphrase Identification with Deep Learning: A Review of Datasets and Methods
por: Zhou, Chao, et al.
Publicado: (2022)

A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs
por: Mersha, Melkamu Abay, et al.
Publicado: (2025)

Learning to Ponder: Adaptive Reasoning in Latent Space
por: He, Yixin, et al.
Publicado: (2025)

LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks
por: Fleshman, William, et al.
Publicado: (2025)

Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
por: Zhou, Yue, et al.
Publicado: (2024)

"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing
por: Rawte, Vipula, et al.
Publicado: (2024)

Contextual Categorization Enhancement through LLMs Latent-Space
por: Bettouche, Zineddine, et al.
Publicado: (2024)

Interpretability of Language Models via Task Spaces
por: Weber, Lucas, et al.
Publicado: (2024)

Multi-Stage Segmentation and Cascade Classification Methods for Improving Cardiac MRI Analysis
por: Slobodzian, Vitalii, et al.
Publicado: (2024)

Explainable AI: XAI-Guided Context-Aware Data Augmentation
por: Mersha, Melkamu Abay, et al.
Publicado: (2025)

DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
por: Xiang, Jianxiang, et al.
Publicado: (2024)

Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation
por: Chang, Lufan
Publicado: (2025)

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
por: Huo, Jiahao, et al.
Publicado: (2026)

PARAPHRASUS : A Comprehensive Benchmark for Evaluating Paraphrase Detection Models
por: Michail, Andrianos, et al.
Publicado: (2024)