Pith. sign in

REVIEW 9 cited by

ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.08676 v3 pith:YI2TVPJK submitted 2024-04-06 cs.CL cs.CYcs.LG

classification cs.CLcs.CYcs.LG
keywords safetyllmsalertlanguagemodelstaxonomyadversarialassess
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may contribute to harm to individuals or society. This principle applies to both normal and adversarial use. In response, we introduce ALERT, a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It is designed to evaluate the safety of LLMs through red teaming methodologies and consists of more than 45k instructions categorized using our novel taxonomy. By subjecting LLMs to adversarial testing scenarios, ALERT aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models. Furthermore, the fine-grained taxonomy enables researchers to perform an in-depth evaluation that also helps one to assess the alignment with various policies. In our experiments, we extensively evaluate 10 popular open- and closed-source LLMs and demonstrate that many of them still struggle to attain reasonable levels of safety.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

    cs.AI 2026-07 conditional novelty 6.5 of 10

    A human-in-the-loop audit of system prompts from 88 commercial AI products finds protective instructions nearly universal yet incomplete, with ~40% of products containing at least one user-harmful directive.

  2. Beyond Knowledge to Agency: Evaluating Expertise, Autonomy, and Integrity in Finance with CNFinBench

    cs.CE 2025-12 conditional novelty 6.0 of 10

    CNFinBench finds LLMs lose about 15 points from single modules to full agentic execution chains, and their financial-compliance violations surge roughly 160-170% by the second round of multi-turn adversarial attacks.

  3. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  4. YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models

    cs.HC 2025-09 conditional novelty 6.0 of 10

    Introduces YAIR, a youth-GenAI risk benchmark, and YouthSafe, a fine-tuned classifier with AUPRC 0.94 on it, though it compares a trained model to untrained baselines.

  5. IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement

    cs.AI 2025-08 reject novelty 6.0 of 10

    IntentionReasoner adds four-level intent classification and targeted query rewriting to LLM guardrails, reporting state-of-the-art harm detection and near-zero jailbreak success.

  6. NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

    cs.CR 2025-09 conditional novelty 5.0 of 10

    A visualization system traces jailbreak attacks through LLM layers and neurons, then fine-tunes the vulnerable neurons to reduce attack success while preserving general ability.

  7. The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails

    cs.CR 2026-08 conditional novelty 4.0 of 10

    Adversarial images aligned with the latent distribution of unsafe content can force multimodal guard models to falsely reject safe user requests with up to 84% success.

  8. A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structured literature survey concluding that reasoning capabilities do not automatically make LLMs more trustworthy and can introduce new vulnerabilities in safety, robustness, and privacy.

  9. The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs

    cs.CL 2025-06 conditional novelty 3.0 of 10

    A structured survey of LLM safety evaluation that proposes a why/what/where/how taxonomy and catalogs metrics, datasets, benchmarks, evaluators, and frameworks.

Pith tools