Cover Image

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Junyuan, Duan, Jinhao, Zhang, Chenhui, Li, Zhangheng, Xie, Chulin, Lieberman, Kelsey, Diffenderfer, James, Bartoldson, Brian, Jaiswal, Ajay, Xu, Kaidi, Kailkhura, Bhavya, Hendrycks, Dan, Song, Dawn, Wang, Zhangyang, Li, Bo
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
by: Duan, Jinhao, et al.
Published: (2025)

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
by: Bartoldson, Brian R., et al.
Published: (2024)

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
by: Li, Zhangheng, et al.
Published: (2024)

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
by: Hong, Junyuan, et al.
Published: (2023)

TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
by: Duan, Jinhao, et al.
Published: (2025)

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
by: Wang, Boxin, et al.
Published: (2023)

GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
by: Duan, Jinhao, et al.
Published: (2024)

Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness
by: Wang, Zeyu, et al.
Published: (2025)

End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
by: Ma, Shaocong, et al.
Published: (2024)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
by: Pal, Soumyadeep, et al.
Published: (2025)

Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
by: Christopher, Jacob K, et al.
Published: (2024)

Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
by: Yang, Hongru, et al.
Published: (2024)

Compressing LLMs: The Truth is Rarely Pure and Never Simple
by: Jaiswal, Ajay, et al.
Published: (2023)

Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models
by: Arif, Huzaifa, et al.
Published: (2025)

Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
by: McDonald, Tavish, et al.
Published: (2025)

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
by: Duan, Jinhao, et al.
Published: (2023)

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
by: Bartoldson, Brian, et al.
Published: (2025)

LLM-PBE: Assessing Data Privacy in Large Language Models
by: Li, Qinbin, et al.
Published: (2024)

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
by: Xu, Chejian, et al.
Published: (2025)

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
by: Zheng, Haizhong, et al.
Published: (2025)

ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
by: Zheng, Haizhong, et al.
Published: (2024)

Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations
by: Cheng, Hao, et al.
Published: (2021)

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
by: Jia, Jinghan, et al.
Published: (2024)

AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
by: Cai, Zikui, et al.
Published: (2025)

IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
by: Fan, Haozhi, et al.
Published: (2026)

Error Analysis of ZFP Compression for Floating-Point Data
by: Diffenderfer, James, et al.
Published: (2018)

Aggressive Compression Enables LLM Weight Theft
by: Brown, Davis, et al.
Published: (2026)

Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
by: Liu, Sijia, et al.
Published: (2026)

Stability Analysis of Inline ZFP Compression for Floating-Point Data in Iterative Methods
by: Fox, Alyson, et al.
Published: (2020)

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
by: Wang, Zijun, et al.
Published: (2025)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
by: Zhang, Zhuoxuan, et al.
Published: (2025)

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
by: Chen, Aochuan, et al.
Published: (2023)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
by: Geiping, Jonas, et al.
Published: (2025)

FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling
by: Chen, Cheng, et al.
Published: (2020)

Improving Robustness In Sparse Autoencoders via Masked Regularization
by: Narayanaswamy, Vivek, et al.
Published: (2026)

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
by: Chen, Cheng, et al.
Published: (2021)

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
by: Yin, Lu, et al.
Published: (2023)

LLaGA: Large Language and Graph Assistant
by: Chen, Runjin, et al.
Published: (2024)

TrustLLM: Trustworthiness in Large Language Models
by: Huang, Yue, et al.
Published: (2024)

A Study of Student Dependency on Artificial Intelligence Applications in their Education: With Reference to Indore City
by: Ajay Jaiswal
Published: (2025)