Imagen de Portada

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tan, Chenchen, Li, Xinghao, Cui, Shujie, Qu, Youyang, Chen, Cunjian, Gao, Longxiang
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
por: Tan, Chenchen, et al.
Publicado: (2025)

When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers
por: Zhang, Zhaoxin, et al.
Publicado: (2025)

Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
por: Qu, Youyang, et al.
Publicado: (2024)

Unsupervised Layer-Wise Dynamic Test Time Adaptation for LLMs
por: Xu, Longhuan, et al.
Publicado: (2026)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
por: Kadhe, Swanand Ravindra, et al.
Publicado: (2024)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
por: Yang, Zhen, et al.
Publicado: (2025)

Less is More for Long Document Summary Evaluation by LLMs
por: Wu, Yunshu, et al.
Publicado: (2023)

Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
por: Banayeeanzade, Amin, et al.
Publicado: (2026)

Soundwave: Less is More for Speech-Text Alignment in LLMs
por: Zhang, Yuhao, et al.
Publicado: (2025)

Less is More: High-value Data Selection for Visual Instruction Tuning
por: Liu, Zikang, et al.
Publicado: (2024)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
por: Chen, Kang, et al.
Publicado: (2025)

More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs
por: Gude, Adrián, et al.
Publicado: (2026)

Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
por: Hoang, Duy C., et al.
Publicado: (2024)

Less Is More: Elevating RAG via Performance-Driven Context Compression
por: Cui, Ziqiang, et al.
Publicado: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
por: Wu, Yuyang, et al.
Publicado: (2025)

Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
por: Salahuddin, Salahuddin, et al.
Publicado: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
por: Zhao, Weixiang, et al.
Publicado: (2025)

Less is More: Adaptive Program Repair with Bug Localization and Preference Learning
por: Dai, Zhenlong, et al.
Publicado: (2025)

Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
por: Bao, Jianzhu, et al.
Publicado: (2026)

LIMO: Less is More for Reasoning
por: Ye, Yixin, et al.
Publicado: (2025)

Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs
por: Banerjee, Mohor, et al.
Publicado: (2025)

Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners
por: Zhang, Shimao, et al.
Publicado: (2024)

Fine-Grained Activation Steering: Steering Less, Achieving More
por: Feng, Zijian, et al.
Publicado: (2026)

LIMR: Less is More for RL Scaling
por: Li, Xuefeng, et al.
Publicado: (2025)

Less is More: Resource-Efficient Low-Rank Adaptation
por: Tian, Chunlin, et al.
Publicado: (2025)

More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles
por: Chen, Ruibo, et al.
Publicado: (2026)

Disclosure and Mitigation of Gender Bias in LLMs
por: Dong, Xiangjue, et al.
Publicado: (2024)

More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
por: Yadav, Advait, et al.
Publicado: (2026)

Less is More: The Effectiveness of Compact Typological Language Representations
por: Ng, York Hay, et al.
Publicado: (2025)

How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
por: Qiu, Xinchi, et al.
Publicado: (2024)

Sell More, Play Less: Benchmarking LLM Realistic Selling Skill
por: Su, Xuanbo, et al.
Publicado: (2026)

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
por: Liu, Jinzhe, et al.
Publicado: (2025)

Geometric-disentangelment Unlearning
por: Zhou, Duo, et al.
Publicado: (2025)

Guardrail Baselines for Unlearning in LLMs
por: Thaker, Pratiksha, et al.
Publicado: (2024)

More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding
por: Tang, Yuan, et al.
Publicado: (2024)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
por: Ye, Jiayuan, et al.
Publicado: (2026)

Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition
por: Mansour, Ayman
Publicado: (2026)

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
por: Song, Dingjie, et al.
Publicado: (2024)

Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation
por: Gkoumas, Dimitris, et al.
Publicado: (2024)

LimRank: Less is More for Reasoning-Intensive Information Reranking
por: Song, Tingyu, et al.
Publicado: (2025)