Copertina

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Du, Yanrui, Fan, Fenglei, Zhao, Sendong, Cao, Jiawei, Liu, Ting, Qin, Bing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
di: Du, Yanrui, et al.
Pubblicazione: (2024)

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
di: Du, Yanrui, et al.
Pubblicazione: (2024)

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
di: Du, Yanrui, et al.
Pubblicazione: (2025)

Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
di: Du, Yanrui, et al.
Pubblicazione: (2023)

Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
di: Du, Yanrui, et al.
Pubblicazione: (2023)

MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
di: Guo, Haoqiang, et al.
Pubblicazione: (2024)

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
di: Chen, Yuhan, et al.
Pubblicazione: (2023)

AS-ES Learning: Towards Efficient CoT Learning in Small Models
di: Xi, Nuwa, et al.
Pubblicazione: (2024)

SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation
di: Wang, Haochun, et al.
Pubblicazione: (2026)

MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
di: Aviv, Gilad, et al.
Pubblicazione: (2025)

Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing
di: Qiang, Zewen, et al.
Pubblicazione: (2025)

From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
di: Du, Yanrui, et al.
Pubblicazione: (2026)

Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese
di: Wang, Haochun, et al.
Pubblicazione: (2023)

Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis
di: Wang, Haochun, et al.
Pubblicazione: (2024)

LLMs May Perform MCQA by Selecting the Least Incorrect Option
di: Wang, Haochun, et al.
Pubblicazione: (2024)

MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views
di: Cai, Muzhen, et al.
Pubblicazione: (2024)

Manifold-based Verbalizer Space Re-embedding for Tuning-free Prompt-based Classification
di: Wang, Haochun, et al.
Pubblicazione: (2023)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
di: Du, Yanrui, et al.
Pubblicazione: (2026)

META-RAG: Meta-Analysis-Inspired Evidence-Re-Ranking Method for Retrieval-Augmented Generation in Evidence-Based Medicine
di: Sun, Mengzhou, et al.
Pubblicazione: (2025)

Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
di: Wang, Haochun, et al.
Pubblicazione: (2026)

PICOs-RAG: PICO-supported Query Rewriting for Retrieval-Augmented Generation in Evidence-Based Medicine
di: Sun, Mengzhou, et al.
Pubblicazione: (2025)

ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG
di: Li, Jianbo, et al.
Pubblicazione: (2026)

CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
di: Jiang, Yi, et al.
Pubblicazione: (2025)

OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation
di: Jiang, Yi, et al.
Pubblicazione: (2026)

Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language Models
di: Prucs, Ákos, et al.
Pubblicazione: (2025)

M-Eval: A Heterogeneity-Based Framework for Multi-evidence Validation in Medical RAG Systems
di: Sun, Mengzhou, et al.
Pubblicazione: (2025)

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
di: Sun, Shengyin, et al.
Pubblicazione: (2026)

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
di: Xiong, Kai, et al.
Pubblicazione: (2023)

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure
di: Xiao, Boyu, et al.
Pubblicazione: (2026)

Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
di: Lu, Xin, et al.
Pubblicazione: (2024)

Towards Pareto Optimal Throughput in Small Language Model Serving
di: Recasens, Pol G., et al.
Pubblicazione: (2024)

Text Difficulty Study: Do machines behave the same as humans regarding text difficulty?
di: Chen, Bowen, et al.
Pubblicazione: (2022)

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
di: Sun, Zhouhao, et al.
Pubblicazione: (2024)

Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging
di: Hu, Tiancheng, et al.
Pubblicazione: (2025)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
di: Zhao, Weixiang, et al.
Pubblicazione: (2024)

Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns
di: Zhao, Yang, et al.
Pubblicazione: (2024)

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
di: Lu, Xin, et al.
Pubblicazione: (2025)

Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future
di: Chu, Zheng, et al.
Pubblicazione: (2023)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
di: Xiong, Kai, et al.
Pubblicazione: (2024)

Large Language Models Are Still Misled by Simple Bias Ensembles
di: Sun, Zhouhao, et al.
Pubblicazione: (2025)