Copertina

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhai, Naixin, Shao, Pengyang, Zheng, Binbin, Yang, Yonghui, Shen, Fei, Bai, Long, Yang, Xun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
di: Shao, Pengyang, et al.
Pubblicazione: (2026)

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
di: Liu, Kaiyuan, et al.
Pubblicazione: (2026)

CLUE: Conflict-guided Localization for LLM Unlearning Framework
di: Chen, Hang, et al.
Pubblicazione: (2025)

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
di: Li, Yang, et al.
Pubblicazione: (2022)

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
di: Feng, Ruixiang, et al.
Pubblicazione: (2026)

Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
di: Xiao, Zeguan, et al.
Pubblicazione: (2026)

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
di: Chang, Hwan, et al.
Pubblicazione: (2025)

How Does Prefix Matter in Reasoning Model Tuning?
di: Tomar, Raj Vardhan, et al.
Pubblicazione: (2026)

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
di: Liang, Qiao, et al.
Pubblicazione: (2026)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
di: Guo, Phillip, et al.
Pubblicazione: (2024)

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

PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
di: Chen, Mengzhao, et al.
Pubblicazione: (2024)

Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
di: Lee, Hwiyeong, et al.
Pubblicazione: (2025)

Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT
di: Lee, Wonhyuk, et al.
Pubblicazione: (2025)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
di: Sun, Yiliu, et al.
Pubblicazione: (2025)

CURE:Circuit-Aware Unlearning for LLM-based Recommendation
di: Chen, Ziheng, et al.
Pubblicazione: (2026)

GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
di: Havrilla, Alex, et al.
Pubblicazione: (2024)

ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition
di: Ye, Lu, et al.
Pubblicazione: (2024)

GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond
di: Zheng, Shen, et al.
Pubblicazione: (2023)

Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
di: Xiao, Yang, et al.
Pubblicazione: (2026)

PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel
di: Yi, Jinjun, et al.
Pubblicazione: (2025)

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
di: Wang, Haonan, et al.
Pubblicazione: (2025)

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
di: Sondej, Filip, et al.
Pubblicazione: (2025)

LocalSUG: City-Preference-Enhanced LLM for Query Suggestion in Local-Life Services
di: Chen, Jinwen, et al.
Pubblicazione: (2026)

UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective
di: Xiong, Jing, et al.
Pubblicazione: (2024)

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
di: Wu, Jiawei, et al.
Pubblicazione: (2026)

QuantClaw: Precision Where It Matters for OpenClaw
di: Zhang, Manyi, et al.
Pubblicazione: (2026)

Detecting Prefix Bias in LLM-based Reward Models
di: Kumar, Ashwin, et al.
Pubblicazione: (2025)

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
di: Yang, Zhengbang, et al.
Pubblicazione: (2026)

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
di: Bin, Yi, et al.
Pubblicazione: (2025)

LaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation
di: Yang, Jiabing, et al.
Pubblicazione: (2025)

Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
di: Xiao, Zeguan, et al.
Pubblicazione: (2026)

Label Words as Local Task Vectors in In-Context Learning
di: Zheng, Bowen, et al.
Pubblicazione: (2024)

Dolphin-CN-Dialect: Where Chinese Dialects Matter
di: Meng, Yangyang, et al.
Pubblicazione: (2026)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
di: Spohn, Philipp, et al.
Pubblicazione: (2025)

Towards Infinite-Long Prefix in Transformer
di: Liang, Yingyu, et al.
Pubblicazione: (2024)

Where to Search: Measure the Prior-Structured Search Space of LLM Agents
di: Song, Zhuo-Yang
Pubblicazione: (2025)

LLM Unlearning with LLM Beliefs
di: Li, Kemou, et al.
Pubblicazione: (2025)

MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking
di: Tang, Tianwen, et al.
Pubblicazione: (2024)