Pith. sign in

REVIEW 24 cited by

SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

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 2402.05044 v4 pith:E65HEJQ2 submitted 2024-02-07 cs.CL cs.AIcs.CRcs.LG

SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

classification cs.CL cs.AIcs.CRcs.LG
keywords salad-benchdefensesafetyattackensuringevaluationlargellms
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In the rapidly evolving landscape of Large Language Models (LLMs), ensuring robust safety measures is paramount. To meet this crucial need, we propose \emph{SALAD-Bench}, a safety benchmark specifically designed for evaluating LLMs, attack, and defense methods. Distinguished by its breadth, SALAD-Bench transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.SALAD-Bench is crafted with a meticulous array of questions, from standard queries to complex ones enriched with attack, defense modifications and multiple-choice. To effectively manage the inherent complexity, we introduce an innovative evaluators: the LLM-based MD-Judge for QA pairs with a particular focus on attack-enhanced queries, ensuring a seamless, and reliable evaluation. Above components extend SALAD-Bench from standard LLM safety evaluation to both LLM attack and defense methods evaluation, ensuring the joint-purpose utility. Our extensive experiments shed light on the resilience of LLMs against emerging threats and the efficacy of contemporary defense tactics. Data and evaluator are released under https://github.com/OpenSafetyLab/SALAD-BENCH.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 24 Pith papers

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

  1. FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

    cs.CR 2026-06 unverdicted novelty 7.0

    FinRED creates an expert-validated benchmark and rubric for financial LLM safety that maps regulatory standards to specific threats and reduces critical false negatives in evaluation from 28 to 12.

  2. Gate AI: LLM Security Benchmark Evaluation Methodology and Results

    cs.LG 2026-06 unverdicted novelty 7.0

    Introduces a cross-validation-based evaluation methodology for LLM security detectors using a global threshold and group-fold leakage checks to avoid per-dataset tuning.

  3. Robust and Efficient Guardrails with Latent Reasoning

    cs.AI 2026-05 unverdicted novelty 7.0

    COLAGUARD matches explicit-reasoning guardrail performance on safety benchmarks while delivering 12.9X speedup and 22.4X token reduction by propagating hidden states instead of generating text.

  4. Non-linear Interventions on Large Language Models

    cs.CL 2026-05 unverdicted novelty 7.0

    Presents a non-linear intervention framework for LLMs with a learning procedure for implicit features, validated on refusal bypass steering showing improved precision over linear baselines.

  5. Self-Mined Hardness for Safety Fine-Tuning

    cs.LG 2026-05 unverdicted novelty 7.0

    Self-mined hardness from model rollouts reduces WildJailbreak attack success rates to 1-3% on Llama models but increases over-refusal on benign prompts, which mixing with adversarially-framed benign prompts partially ...

  6. ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts

    cs.AI 2026-04 unverdicted novelty 7.0

    ARMOR 2025 is a new benchmark with 519 doctrinally grounded prompts across a 12-category OODA-based taxonomy that reveals critical safety gaps in 21 commercial LLMs for military applications.

  7. Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    cs.CR 2026-06 unverdicted novelty 6.0

    Jailbreak attacks suppress Adversarially Compromised Heads in early layers but leave Safety-Aligned Heads robust in mid-layers, enabling competitive detection from persistent activations.

  8. SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

    cs.AI 2026-06 unverdicted novelty 6.0

    SafeSteer restricts reverse KL penalty to safety tokens selected via activation steering, achieving strong safety on seven benchmarks with minimal degradation on five capability benchmarks using only 100 harmful sampl...

  9. LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

    cs.CR 2026-05 conditional novelty 6.0

    LPG compresses policy deliberation into 10 latent tokens to reach 84.5% safety accuracy and 11x speedup over explicit reasoning baselines on guardrail benchmarks.

  10. Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks

    cs.AI 2026-05 unverdicted novelty 6.0

    Toxicity benchmarks for LLMs produce inconsistent results when task type, input domain, or model changes, revealing intrinsic evaluation biases.

  11. Self-Mined Hardness for Safety Fine-Tuning

    cs.LG 2026-05 unverdicted novelty 6.0

    Self-mined hardness from model rollouts lowers WildJailbreak attack success to 1-3% on Llama-3 models while raising over-refusal, mitigated by 1:1 interleaving with benign prompts.

  12. How Sensitive Are Safety Benchmarks to Judge Configuration Choices?

    cs.CL 2026-04 unverdicted novelty 6.0

    LLM judge prompt variations alone shift HarmBench harmful-response rates by up to 24.2 percentage points and produce moderate instability in model safety rankings.

  13. Towards Understanding the Robustness of Sparse Autoencoders

    cs.LG 2026-04 unverdicted novelty 6.0

    Integrating pretrained sparse autoencoders into LLM residual streams reduces jailbreak success rates by up to 5x across multiple models and attacks.

  14. The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

    cs.CR 2026-04 unverdicted novelty 6.0

    ORPO is most effective at misaligning LLMs while DPO excels at realigning them, though it reduces utility, revealing an asymmetry between attack and defense methods.

  15. f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

    cs.LG 2026-02 unverdicted novelty 6.0

    f-GRPO and f-HAL estimate f-divergences between reward-aligned and reward-unaligned response distributions and prove expected reward improvement for general LLM alignment.

  16. Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

    cs.CL 2025-11 unverdicted novelty 6.0

    EvoSynth evolves code-based jailbreak algorithms via multi-agent self-correction, reaching 85.5% ASR on Claude-Sonnet-4.5 and 95.9% average across targets with greater diversity.

  17. WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

    cs.CL 2024-06 conditional novelty 6.0

    WildGuard is a new open moderation model and dataset for LLM safety that identifies harmful prompts, risky responses, and refusal rates, achieving SOTA open-source performance and sometimes exceeding GPT-4 while cutti...

  18. Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation

    cs.CL 2026-04 conditional novelty 5.5

    Qwen Guard (4B) reaches 83.97% recall on a 79k NIST-aligned safety benchmark while larger models such as Llama Guard 12B and GPT-OSS 20B miss up to 75% of unsafe content; model size does not predict detection performance.

  19. Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    cs.CR 2026-06 unverdicted novelty 5.0

    Jailbreak attacks suppress Adversarially Compromised Heads in early layers but leave Safety-Aligned Heads active in mid-layers, producing robust harmful features usable for competitive training-free detection.

  20. DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

    cs.CR 2026-05 unverdicted novelty 5.0

    DataShield scores training samples by their contribution to increased LLM response compliance and filters high-risk ones using a compliance vector and layer-specific CAS metric.

  21. A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts

    cs.CR 2026-05 accept novelty 5.0

    The paper releases a 1,554-prompt consensus-labeled bank separating executable malicious code requests from security knowledge requests, validated by five-model majority labeling with Fleiss' kappa of 0.876.

  22. Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control

    cs.LG 2026-02 unverdicted novelty 5.0

    ShaPO improves LLM safety robustness over standard preference optimization by enforcing worst-case objectives via selective geometry control at token and reward levels.

  23. Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

    cs.LG 2026-05 unverdicted novelty 4.0

    Opir introduces efficient multi-task encoder models trained on a 996-category safety taxonomy that match or exceed larger baselines on most safety benchmarks while using under 100M parameters for edge variants.

  24. ShieldGemma: Generative AI Content Moderation Based on Gemma

    cs.CL 2024-07 unverdicted novelty 4.0

    ShieldGemma delivers a family of Gemma2-based classifiers that outperform Llama Guard and WildCard on public safety benchmarks while introducing a synthetic-data curation pipeline for safety tasks.