{"total":57,"rows":[{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2408.05636","title":"Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion","created":"2024-08-10","cited_by_count":57,"area":"inference"},{"id":"2504.04715","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2407.09141","title":"Accuracy is Not All You Need","created":"2024-07-12","cited_by_count":31,"area":null},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"area":"moe"},{"id":"2409.11055","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2512.17319","title":"A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs","created":"2025-12-19","cited_by_count":11,"area":"lr"},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2405.17512","title":"On Fairness of Low-Rank Adaptation of Large Models","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2410.22118","title":"The Impact of Inference Acceleration on Bias of LLMs","created":"2024-10-29","cited_by_count":9,"area":"inference"},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2602.06181","title":"Investigating Social Bias Changes in Quantized Language Models","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2606.15980","title":"Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2405.15984","title":"Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning","created":"2024-05-24","cited_by_count":4,"area":"rag"},{"id":"2405.19458","title":"MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection","created":"2024-05-29","cited_by_count":4,"area":"diffusion"},{"id":"2503.04982","title":"LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression","created":"2025-03-06","cited_by_count":4,"area":"mllm"},{"id":"2508.18088","title":"How Quantization Shapes Bias in Large Language Models","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2505.13963","title":"Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2507.17725","title":"On the Interaction of Compressibility and Adversarial Robustness","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2509.00096","title":"Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2511.19523","title":"EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question Answering","created":"2025-11-24","cited_by_count":2,"area":"alignment"},{"id":"2605.08137","title":"Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2607.12792","title":"Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels","created":"2026-07-14","cited_by_count":2,"area":"safety"},{"id":"2608.11981","title":"Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2505.05619","title":"LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities","created":"2025-05-08","cited_by_count":1,"area":"safety"},{"id":"2506.08487","title":"Beyond Bias Scores: Unmasking Vacuous Neutrality in Small Language Models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2601.12033","title":"Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2606.10154","title":"Quality Is Not a Safety Proxy Under Quantization","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.17872","title":"AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2607.01444","title":"On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain","created":"2026-07-01","cited_by_count":1,"area":"moe"},{"id":"2607.04640","title":"Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models","created":"2026-07-06","cited_by_count":1,"area":"alignment"},{"id":"2608.19670","title":"The Asymmetric Harms of LLM Compression","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2508.13533","title":"Models in the Same Family are NOT Trust-Equivalent","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.15206","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.22099","title":"Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2511.22483","title":"Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2603.25035","title":"Mechanistically Interpreting Compression in Vision-Language Models","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2605.27763","title":"A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.13088","title":"Securing LLMs in the Wild: Privacy and Security Challenges at the Edge","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2608.02940","title":"When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.01023","title":"AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.23587","title":"On the Efficiency-Safety Dilemma in Large Reasoning Models","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.33898","title":"No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38106","title":"Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01058","title":"MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.02462","title":"Capability Scaling-Down Laws for LLM Compression","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15218","title":"Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}