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

arXiv: https://arxiv.org/abs/2403.15447 · HTML: https://mlsanity.com/paper/2403.15447/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 65 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 30 of 56)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [QuIP: 2-Bit Quantization of Large Language Models With Guarantees](https://mlsanity.com/paper/2307.13304/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)

## Built on by (most cited first, 30 of 57)

- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?](https://mlsanity.com/paper/2407.21792/) (2024)
- [Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion](https://mlsanity.com/paper/2408.05636/) (2024)
- [Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs](https://mlsanity.com/paper/2504.04715/) (2025)
- [Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression](https://mlsanity.com/paper/2407.04965/) (2024)
- [Accuracy is Not All You Need](https://mlsanity.com/paper/2407.09141/) (2024)
- [Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations](https://mlsanity.com/paper/2504.05586/) (2025)
- [Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant](https://mlsanity.com/paper/2409.11055/) (2024)
- [Quantized Delta Weight Is Safety Keeper](https://mlsanity.com/paper/2411.19530/) (2024)
- [Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2505.01043/) (2025)
- [A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs](https://mlsanity.com/paper/2512.17319/) (2025)
- [CSPLADE: Learned Sparse Retrieval with Causal Language Models](https://mlsanity.com/paper/2504.10816/) (2025)
- [On Fairness of Low-Rank Adaptation of Large Models](https://mlsanity.com/paper/2405.17512/) (2024)
- [The Impact of Inference Acceleration on Bias of LLMs](https://mlsanity.com/paper/2410.22118/) (2024)
- [Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs](https://mlsanity.com/paper/2508.19432/) (2025)
- [Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense](https://mlsanity.com/paper/2502.00840/) (2025)
- [Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability](https://mlsanity.com/paper/2504.04215/) (2025)
- [Investigating Social Bias Changes in Quantized Language Models](https://mlsanity.com/paper/2602.06181/) (2026)
- [Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness](https://mlsanity.com/paper/2606.15980/) (2026)
- [Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning](https://mlsanity.com/paper/2405.15984/) (2024)
- [MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection](https://mlsanity.com/paper/2405.19458/) (2024)
- [LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression](https://mlsanity.com/paper/2503.04982/) (2025)
- [How Quantization Shapes Bias in Large Language Models](https://mlsanity.com/paper/2508.18088/) (2025)
- [Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall](https://mlsanity.com/paper/2505.13963/) (2025)
- [Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models](https://mlsanity.com/paper/2506.20251/) (2025)
- [On the Interaction of Compressibility and Adversarial Robustness](https://mlsanity.com/paper/2507.17725/) (2025)
- [Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs](https://mlsanity.com/paper/2509.00096/) (2025)
- [EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question Answering](https://mlsanity.com/paper/2511.19523/) (2025)
- [Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI](https://mlsanity.com/paper/2605.08137/) (2026)
- [Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels](https://mlsanity.com/paper/2607.12792/) (2026)

## Abstract (arXiv)

Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected. This study conducts the first, thorough evaluation of three (3) leading LLMs using five (5) SoTA compression techniques across eight (8) trustworthiness dimensions. Our experiments highlight the intricate interplay between compression and trustworthiness, revealing some interesting patterns. We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously. For instance, a 4-bit quantized model retains the trustworthiness of its original counterpart, but model pruning significantly degrades trustworthiness, even at 50% sparsity. Moreover, employing quantization within a moderate bit range could unexpectedly improve certain trustworthiness dimensions such as ethics and fairness. Conversely, extreme quantization to very low bit levels (3 bits) tends to reduce trustworthiness significantly. This increased risk cannot be uncovered by looking at benign performance alone, in turn, mandating comprehensive trustworthiness evaluation in practice. These findings culminate in practical recommendations for simultaneously achieving high utility, efficiency, and trustworthiness in LLMs. Code and models are available at https://decoding-comp-trust.github.io.