Cover Image

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Dongxin, Wu, Jikun, Yiu, Siu Ming
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence 68T07, 68T50, 68T05 I.2.7; I.2.6; I.2.0
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
by: Guo, Dongxin, et al.
Published: (2026)

EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
by: Guo, Dongxin, et al.
Published: (2026)

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure
by: Sarkar, Nilesh, et al.
Published: (2026)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
by: Basu, Abhinaba
Published: (2026)

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
by: Breneur, Oleksandr Marchenko, et al.
Published: (2026)

Rethinking the Multilingual Reasoning Gap with Layer Swap
by: Lasbordes, Maxence, et al.
Published: (2026)

Harnessing non-adversarial robustness in large language models
by: Zhou, Qinghua, et al.
Published: (2026)

Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
by: Imanov, Olaf Yunus Laitinen
Published: (2026)

CLMN: Concept based Language Models via Neural Symbolic Reasoning
by: Yang, Yibo
Published: (2025)

Large Language Models Report Subjective Experience Under Self-Referential Processing
by: Berg, Cameron, et al.
Published: (2025)

JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector Manipulation
by: Huang, Yingbing, et al.
Published: (2025)

How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models
by: Borobia, Hector, et al.
Published: (2026)

AIPsy-Affect: A Keyword-Free Clinical Stimulus Battery for Mechanistic Interpretability of Emotion in Language Models
by: Keeman, Michael
Published: (2026)

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
by: Henry, James
Published: (2026)

Product-of-Experts Training Reduces Dataset Artifacts in Natural Language Inference
by: Mathew, Aby Mammen
Published: (2026)

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds
by: Alpay, Faruk, et al.
Published: (2026)

Inference acceleration for large language models using "stairs" assisted greedy generation
by: Grigaliūnas, Domas, et al.
Published: (2024)

Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting
by: Imanov, Olaf Yunus Laitinen, et al.
Published: (2026)

Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
by: Badshah, Sher, et al.
Published: (2024)

Unpacking Hateful Memes: Presupposed Context and False Claims
by: Cai, Weibin, et al.
Published: (2025)

Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
by: Pather, Kaviraj, et al.
Published: (2025)

Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining
by: Cao, Deyu, et al.
Published: (2025)

ProactBench: Beyond What The User Asked For
by: Harfi, Sepehr, et al.
Published: (2026)

SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention
by: Guo, Dongxin, et al.
Published: (2026)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
by: Dang, Kieu, et al.
Published: (2025)

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
by: Lee, Wooin, et al.
Published: (2026)

Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models
by: Vileikytė, Brigita, et al.
Published: (2024)

Linguistic Collapse: Neural Collapse in (Large) Language Models
by: Wu, Robert, et al.
Published: (2024)

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
by: Wang, Yihao, et al.
Published: (2026)

MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
by: Giannini, Federico, et al.
Published: (2026)

Sliced-Wasserstein Distribution Alignment Loss Improves the Ultra-Low-Bit Quantization of Large Language Models
by: Cao, Deyu, et al.
Published: (2026)

mHC-SSM: Manifold-Constrained Hyper-Connections for State Space Language Models with Stream-Specialized Adapters
by: Mutlu, Abdulvahap, et al.
Published: (2026)

Extracting Sentence Embeddings from Pretrained Transformer Models
by: Stankevičius, Lukas, et al.
Published: (2024)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
by: Chen, Yihong, et al.
Published: (2022)

How much do LLMs learn from negative examples?
by: Hamdan, Shadi, et al.
Published: (2025)

Communicative Agents for Slideshow Storytelling Video Generation based on LLMs
by: Fan, Jingxing, et al.
Published: (2025)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
by: Kim, Heejun, et al.
Published: (2026)

Do Reasoning Models Enhance Embedding Models?
by: Chan, Wun Yu, et al.
Published: (2026)

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference
by: Das, Sourav
Published: (2026)

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
by: Garg, Saloni, et al.
Published: (2026)