mlsanityData to 7 Oct 2026

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs

arXiv 2602.13274 ↗First posted 5 Feb 2026cs.AI cs.CLcited by 4

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 2 more
Abstract (arXiv)

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark evaluating 11 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our new robustness test, ETHICS-Contrast, we measure performance via our proposed Unified Moral Safety Score (UMSS), a metric balancing accuracy and safety. Our results show that compact, exemplar-guided scaffolds outperform complex multi-stage reasoning, providing higher UMSS scores and greater robustness at a lower token cost. While multi-turn reasoning proves fragile under perturbations, few-shot exemplars consistently enhance moral stability and jailbreak resistance. ProMoral-Bench establishes a standardized framework for principled, cost-effective prompt engineering.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 18 of its 22 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

18 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework17 Jun
  2. 2024DeepSeek-V3 Technical Report27 Dec
  3. 2023Better Zero-Shot Reasoning with Role-Play Prompting15 Aug
  4. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?25 Feb

Other references · 14

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  6. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  7. 2020Aligning AI With Shared Human Valuescited by 706
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  9. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 191
  10. 2022Holistic Evaluation of Language Modelscited by 115
  11. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 100
  12. 2025Command A: An Enterprise-Ready Large Language Modelcited by 57
2 more
  1. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
  2. 2023Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoningcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026How Sensitive Are Safety Benchmarks to Judge Configuration Choices?cited by 3
  2. 2026Visuals Lie, Consistency Speaks: Disentangling Spatial Attention from Reliability in Vision-Language Modelscited by 0
  3. 2026A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragilitycited by 0
  4. 2026When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
  2. 2026Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
  3. 2025You Don't Need Prompt Engineering Anymore: The Prompting Inversion
  4. 2025Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
  5. 2025Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
  6. 2024MoralBench: Moral Evaluation of LLMs
  7. 2025The Future of MLLM Prompting is Adaptive: A Comprehensive Experimental Evaluation of Prompt Engineering Methods for Robust Multimodal Performance
  8. 2026Right or Wrong, Models Comply: Directional Blindness in LLM Moral Judgment