Image de couverture de livre

PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rahulamathavan, Yogachandran, Farooq, Misbah, De Silva, Varuna
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
par: Herath, Charuka, et autres
Publié: (2025)

QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
par: Herath, Charuka, et autres
Publié: (2026)

Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
par: Rahulamathavan, Yogachandran, et autres
Publié: (2026)

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users
par: Rahulamathavan, Yogachandran, et autres
Publié: (2023)

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
par: Dhaini, Mahdi, et autres
Publié: (2025)

Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
par: Fragkathoulas, Christos, et autres
Publié: (2024)

Support-Contra Asymmetry in LLM Explanations
par: Patil, Avinash
Publié: (2025)

Evaluating Causal Explanation in Medical Reports with LLM-Based and Human-Aligned Metrics
par: Cho, Yousang, et autres
Publié: (2025)

Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviour
par: Alsaleh, Tareq, et autres
Publié: (2025)

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
par: Conti, Lina, et autres
Publié: (2025)

Enhancing Federated Learning Convergence with Dynamic Data Queue and Data Entropy-driven Participant Selection
par: Herath, Charuka, et autres
Publié: (2024)

Token Masking Improves Transformer-Based Text Classification
par: Xu, Xianglong, et autres
Publié: (2025)

Concept Based Continuous Prompts for Interpretable Text Classification
par: Chen, Qian, et autres
Publié: (2024)

Counterfactual Simulatability of LLM Explanations for Generation Tasks
par: Limpijankit, Marvin, et autres
Publié: (2025)

LLM Self-Explanations Fail Semantic Invariance
par: Szeider, Stefan
Publié: (2026)

LLM-as-a-Judge for Time Series Explanations
par: Sivalingam, Preetham, et autres
Publié: (2026)

STRUX: An LLM for Decision-Making with Structured Explanations
par: Lu, Yiming, et autres
Publié: (2024)

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
par: Huang, Guanhua, et autres
Publié: (2024)

One Size Does Not Fit All: Exploring Variable Thresholds for Distance-Based Multi-Label Text Classification
par: Van Nooten, Jens, et autres
Publié: (2025)

A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers
par: McAleese, Stephen, et autres
Publié: (2024)

Distilling Text Style Transfer With Self-Explanation From LLMs
par: Zhang, Chiyu, et autres
Publié: (2024)

Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning
par: Liu, Menglin, et autres
Publié: (2024)

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
par: Niimi, Junichiro
Publié: (2025)

CoCoP: Enhancing Text Classification with LLM through Code Completion Prompt
par: Mohajeri, Mohammad Mahdi, et autres
Publié: (2024)

Explainability-Based Token Replacement on LLM-Generated Text
par: Mohammadi, Hadi, et autres
Publié: (2025)

PE: A Poincare Explanation Method for Fast Text Hierarchy Generation
par: Chen, Qian, et autres
Publié: (2024)

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
par: Zhang, Ruohong, et autres
Publié: (2023)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
par: Quan, Xin, et autres
Publié: (2025)

Cross-Attention is Half Explanation in Speech-to-Text Models
par: Papi, Sara, et autres
Publié: (2025)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
par: Shu, Huizhen, et autres
Publié: (2025)

Interpretable Text Embeddings and Text Similarity Explanation: A Survey
par: Opitz, Juri, et autres
Publié: (2025)

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
par: Wojciechowski, Adam, et autres
Publié: (2024)

Towards Understanding the Robustness of LLM-based Evaluations under Perturbations
par: Chaudhary, Manav, et autres
Publié: (2024)

Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
par: Yousefiramandi, Amirhossein, et autres
Publié: (2025)

Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations
par: Gajcin, Jasmina, et autres
Publié: (2025)

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
par: Gero, Zelalem, et autres
Publié: (2024)

LLM Based Sentiment Classification From Bangladesh E-Commerce Reviews
par: Tabassum, Sumaiya
Publié: (2025)

A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations
par: Zhao, Lingjun, et autres
Publié: (2025)

Political Leaning and Politicalness Classification of Texts
par: Volf, Matous, et autres
Publié: (2025)

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
par: Djiré, Albérick Euraste, et autres
Publié: (2025)