How Does Thinking Mode Change LLM Moral Judgments? A Controlled Instant-vs-Thinking Comparison Across Five Frontier Models
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
We evaluate whether enabling provider-exposed reasoning mode changes moral judgments within the same model checkpoint. Across 100 moral-judgment scenarios and five frontier reasoning-trained LLMs (Claude Sonnet 4.6, GPT 5.5, Gemini 3 Flash, DeepSeek V3.1, and Qwen3.5 397B), aggregate binary-verdict agreement remains high and statistically indistinguishable between instant and thinking modes (Krippendorff's alpha = 0.78 vs. 0.79). However, disagreement is concentrated in 21 model-disputed scenarios, where instant-mode agreement is near chance (alpha = 0.08). On these scenarios, reasoning directionally narrows cross-model disagreement, increasing mean pairwise agreement from 5.4 to 6.7 out of 10. Reasoning also reduces demographic-judgment inconsistency in three of five models and does not increase it for any model. Across all five model families, reasoning changes self-labeled ethical frameworks more often than binary verdicts.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 8 of its 16 references that are in the map. First posted on arXiv 6 May 2026.
Builds on
8 of 16 references.
References · 8
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
- 2020Aligning AI With Shared Human Valuescited by 706
- 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
- 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
- 2020Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequencescited by 133
- 2023Moral Foundations of Large Language Modelscited by 84
- 2022ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situationscited by 36
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
- 2025The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas
- 2025Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
- 2026Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs
- 2025Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework
- 2026Incoherent by Design? On the Moral Self-Consistency of LLMs
- 2025"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
- 2023Exploring the psychology of LLMs' Moral and Legal Reasoning