mlsanityData to 14 Oct 2026

HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment

arXiv 2411.06835 ↗First posted 11 Nov 2024cs.CL cs.CRcited by 9

On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks

also in 1 more
Abstract (arXiv)

With the introduction of the transformers architecture, LLMs have revolutionized the NLP field with ever more powerful models. Nevertheless, their development came up with several challenges. The exponential growth in computational power and reasoning capabilities of language models has heightened concerns about their security. As models become more powerful, ensuring their safety has become a crucial focus in research. This paper aims to address gaps in the current literature on jailbreaking techniques and the evaluation of LLM vulnerabilities. Our contributions include the creation of a novel dataset designed to assess the harmfulness of model outputs across multiple harm levels, as well as a focus on fine-grained harm-level analysis. Using this framework, we provide a comprehensive benchmark of state-of-the-art jailbreaking attacks, specifically targeting the Vicuna 13B v1.5 model. Additionally, we examine how quantization techniques, such as AWQ and GPTQ, influence the alignment and robustness of models, revealing trade-offs between enhanced robustness with regards to transfer attacks and potential increases in vulnerability on direct ones. This study aims to demonstrate the influence of harmful input queries on the complexity of jailbreaking techniques, as well as to deepen our understanding of LLM vulnerabilities and improve methods for assessing model robustness when confronted with harmful content, particularly in the context of compression strategies.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 11 of its 14 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

11 of 14 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 10

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  3. 2023PaLM 2 Technical Reportcited by 1,162
  4. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  5. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  6. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 505
  7. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 498
  8. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  9. 2024Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Modelscited by 44
  10. 2024Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomescited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Modelscited by 18
  2. 2025Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMscited by 9
  3. 2025Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defensecited by 7
  4. 2026FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequencescited by 3
  5. 2025Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Modelscited by 2
  6. 2026Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protectioncited by 1
  7. 2025Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challengescited by 0
  8. 2026When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMscited by 0
  9. 2026On the Efficiency-Safety Dilemma in Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
  2. 2025On Jailbreaking Quantized Language Models Through Fault Injection Attacks
  3. 2025Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge
  4. 2024Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings
  5. 2025Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
  6. 2025When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers
  7. 2024Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
  8. 2023Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models