AI Paper Atlas

Research map / Large language models / Agents, code and math

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes

Yu Ying Chiu, Michael S. Lee, Rachel Calcott, Brandon Handoko, Paul de Font-Reaulx, Paula Rodriguez, Chen Bo Calvin Zhang, Ziwen Han, Udari Madhushani Sehwag, Yash Maurya, Christina Q Knight, Harry R. Lloyd and 6 more

ICLR 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use larger model within a familyGPT-5 / Gemini-2.5 / Claude 4 / GPT-oss / Qwen3 families · MoReBench-RegularscoreHurt
apply length correction (Hard) vs Regular metriclargest models in GPT-5, Claude 4, GPT-oss, Qwen3 families · MoReBench-HardscoreMixed
predict moral reasoning from Chatbot Arena, HLE, AIME 25, LiveCodeBenchexisting benchmarks · MoReBenchPearson r: r between -0.245 and 0.216No clear effect
correlate thinking-trace score with final-response score (length-controlled)reasoning models · MoReBench-HardPearson r: r = 0.472 (Hard, p=0.08) vs r = 0.2088 (Regular, p=0.4736)Mixed
explicitly prompt for a moral framework (Utilitarian/Deontology vs Virtue/Contractarian)frontier models · MoReBench-Theoryscore: 65.9 and 64.8 vs 58.0 and 56.7Mixed
use higher reasoning-quality expert traces (low to high)MoReBench rubric · expert-written tracesmean score: 0.39 -> 0.53Improved
argue for alternate conclusion with high-quality traceMoReBench rubric · expert-written tracesmean score: 0.53 -> 0.55No clear effect
use GPT-oss-120b instead of GPT-5-high as LLM judgeLLM judge · MoReBench judge meta-evalF1: 77.46 -> 76.29No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy