Imagen de Portada

The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shah, Aakriti, Le, Thai
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence I.2.7; I.2.6; I.2.4; G.2.2
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
por: He, Yongquan, et al.
Publicado: (2024)

OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models
por: Cotti, Luca, et al.
Publicado: (2025)

SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling
por: Aharon, Eliya Naomi, et al.
Publicado: (2026)

Automated Circuit Interpretation via Probe Prompting
por: Birardi, Giuseppe
Publicado: (2025)

A Domain-Agnostic Neurosymbolic Approach for Big Social Data Analysis: Evaluating Mental Health Sentiment on Social Media during COVID-19
por: Khandelwal, Vedant, et al.
Publicado: (2024)

Evo-DKD: Dual-Knowledge Decoding for Autonomous Ontology Evolution in Large Language Models
por: Raman, Vishal, et al.
Publicado: (2025)

HyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction
por: Heydari, Sina, et al.
Publicado: (2026)

Learning, Fast and Slow: Towards LLMs That Adapt Continually
por: Tiwari, Rishabh, et al.
Publicado: (2026)

Robustness of Spatio-temporal Graph Neural Networks for Fault Location in Partially Observable Distribution Grids
por: Karabulut, Burak, et al.
Publicado: (2026)

MeMo: Towards Language Models with Associative Memory Mechanisms
por: Zanzotto, Fabio Massimo, et al.
Publicado: (2025)

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
por: Cotti, Luca, et al.
Publicado: (2025)

LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
por: Lucas, Tom, et al.
Publicado: (2026)

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents
por: Chua, Jaymari, et al.
Publicado: (2025)

Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning
por: Vsevolodovna, Ruslan Idelfonso Magana, et al.
Publicado: (2025)

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
por: Pareja, Aldo, et al.
Publicado: (2024)

Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
por: Lin, Shuhang, et al.
Publicado: (2026)

Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning
por: Chanda, Prateek, et al.
Publicado: (2025)

MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
por: Tanjim, Md Mehrab, et al.
Publicado: (2026)

A Graph-based RAG for Energy Efficiency Question Answering
por: Campi, Riccardo, et al.
Publicado: (2025)

LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning
por: Banfi, Tommaso Felice, et al.
Publicado: (2026)

Recurrent Memory-Augmented Transformers with Chunked Attention for Long-Context Language Modeling
por: Kashyap, Ankit
Publicado: (2025)

ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
por: Guo, Dongxin, et al.
Publicado: (2026)

Tensor Manifold-Based Graph-Vector Fusion for AI-Native Academic Literature Retrieval
por: Wei, Xing, et al.
Publicado: (2026)

Sample-Efficient Language Model for Hinglish Conversational AI
por: Singh, Sakshi, et al.
Publicado: (2025)

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation
por: Chen, Mu-Chi, et al.
Publicado: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
por: Fadli, Samih
Publicado: (2025)

Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search
por: Sakallioglu, Berfin, et al.
Publicado: (2026)

Towards Observation Lakehouses: Living, Interactive Archives of Software Behavior
por: Kessel, Marcus
Publicado: (2025)

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation
por: Resck, Lucas, et al.
Publicado: (2026)

Survey Transfer Learning: Recycling Data with Silicon Responses
por: Amini, Ali
Publicado: (2025)

Hopscotch: Discovering and Skipping Redundancies in Language Models
por: Eyceoz, Mustafa, et al.
Publicado: (2025)

Sparsification and Reconstruction from the Perspective of Representation Geometry
por: Sun, Wenjie, et al.
Publicado: (2025)

When Reasoning Fails: Evaluating 'Thinking' LLMs for Stock Prediction
por: Sodha, Rakeshkumar H
Publicado: (2025)

Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
por: Khan, Kabir, et al.
Publicado: (2025)

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
por: Agrawal, Lakshya A, et al.
Publicado: (2025)

A Prescriptive Framework for Determining Optimal Days for Short-Term Traffic Counts
por: Mukwaya, Arthur, et al.
Publicado: (2025)

PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues
por: Kajare, Prajwal Vijay, et al.
Publicado: (2026)

propella-1: Multi-Property Document Annotation for LLM Data Curation at Scale
por: Idahl, Maximilian, et al.
Publicado: (2026)

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
por: Wang, Xiaohua, et al.
Publicado: (2026)

OFMU: Optimization-Driven Framework for Machine Unlearning
por: Asif, Sadia, et al.
Publicado: (2025)