Image de couverture de livre

Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lee, Hwiyeong, Hwang, Uiji, Lim, Hyelim, Kim, Taeuk
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CRISP: Persistent Concept Unlearning via Sparse Autoencoders
par: Ashuach, Tomer, et autres
Publié: (2025)

Machine Unlearning for Masked Diffusion Language Models
par: Lee, Georu, et autres
Publié: (2026)

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
par: Ashuach, Tomer, et autres
Publié: (2024)

Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?
par: Collado-Montañez, Jaime, et autres
Publié: (2025)

LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty
par: Zhang, Zhen, et autres
Publié: (2024)

Quantization-Robust LLM Unlearning via Low-Rank Adaptation
par: Abitante, João Vitor Boer, et autres
Publié: (2026)

A Multi-Pass Large Language Model Framework for Precise and Efficient Radiology Report Error Detection
par: Kim, Songsoo, et autres
Publié: (2025)

ConPET: Continual Parameter-Efficient Tuning for Large Language Models
par: Song, Chenyang, et autres
Publié: (2023)

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure
par: Mahmood, Syed Naveed, et autres
Publié: (2026)

A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
par: Gaim, Fitsum, et autres
Publié: (2025)

The Limits of Obliviate: Evaluating Unlearning in LLMs via Stimulus-Knowledge Entanglement-Behavior Framework
par: Shah, Aakriti, et autres
Publié: (2025)

How Do Large Language Models Acquire Factual Knowledge During Pretraining?
par: Chang, Hoyeon, et autres
Publié: (2024)

Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering
par: Toroghi, Armin, et autres
Publié: (2024)

ADAG: Automatically Describing Attribution Graphs
par: Arora, Aryaman, et autres
Publié: (2026)

Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
par: Cui, Wanyun, et autres
Publié: (2025)

AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes
par: Yao, Barry Menglong, et autres
Publié: (2023)

SynSym: A Synthetic Data Generation Framework for Psychiatric Symptom Identification
par: Kang, Migyeong, et autres
Publié: (2026)

Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
par: Vasilev, Stefan, et autres
Publié: (2025)

Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal
par: Jiang, Weipeng, et autres
Publié: (2025)

Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks
par: Vrettos, Konstantinos, et autres
Publié: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
par: Peters, Sydney, et autres
Publié: (2025)

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
par: Yu, Haeun, et autres
Publié: (2024)

Evaluating Large Language Models for Zero-Shot Disease Labeling in CT Radiology Reports Across Organ Systems
par: Garcia-Alcoser, Michael E., et autres
Publié: (2025)

Precise Length Control in Large Language Models
par: Butcher, Bradley, et autres
Publié: (2024)

What Drives Performance in Multilingual Language Models?
par: Nezhad, Sina Bagheri, et autres
Publié: (2024)

Large Language Models for Biomedical Article Classification
par: Proboszcz, Jakub, et autres
Publié: (2026)

REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs
par: Cohen, Liran, et autres
Publié: (2025)

SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading
par: Dinh, Tu Anh, et autres
Publié: (2024)

Strategy Adaptation in Large Language Model Werewolf Agents
par: Nakamori, Fuya, et autres
Publié: (2025)

PL-Guard: Benchmarking Language Model Safety for Polish
par: Krasnodębska, Aleksandra, et autres
Publié: (2025)

Socially Responsible Data for Large Multilingual Language Models
par: Smart, Andrew, et autres
Publié: (2024)

HACK: Hallucinations Along Certainty and Knowledge Axes
par: Simhi, Adi, et autres
Publié: (2025)

Large Language Models for Persian $ \leftrightarrow $ English Idiom Translation
par: Rezaeimanesh, Sara, et autres
Publié: (2024)

Qomhra: A Bilingual Irish and English Large Language Model
par: McInerney, Joseph, et autres
Publié: (2025)

Dialect Normalization using Large Language Models and Morphological Rules
par: Dimakis, Antonios, et autres
Publié: (2025)

Towards Human Understanding of Paraphrase Types in Large Language Models
par: Meier, Dominik, et autres
Publié: (2024)

RUQuant: Towards Refining Uniform Quantization for Large Language Models
par: Liu, Han, et autres
Publié: (2026)

Task Contamination: Language Models May Not Be Few-Shot Anymore
par: Li, Changmao, et autres
Publié: (2023)

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information
par: Park, Seungcheol, et autres
Publié: (2025)

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
par: Ashuach, Tomer, et autres
Publié: (2026)