AI Paper Atlas

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

LogiConBench: Benchmarking Logical Consistencies of LLMs

Zheng CHEN, Chuan Zhou, Fengxiang Cheng, Yip Tin Po, Fenrong Liu, Yisen Wang, Jiajun Chai, Xiaohan Wang, Guojun Yin, Wei Lin, Bo Li, Haoxuan Li and 1 more

ICLR 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 citations (OpenAlex)

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
add 3-shot examples with reasoning paths instead of zero-shot (ablation)14 LLMs · Task 1 discriminativeaverage accuracy: 59.21% -> 67.58%Improved
add 3-shot examples instead of zero-shot (ablation)14 LLMs · Task 1 discriminativeaverage accuracy: 59.21% -> 65.70%Improved
increase statements from k=2 to k=514 LLMs · Task 1 discriminativeaverage accuracy: 66.87% -> 59.59%Hurt
add 3-shot examples with reasoning paths instead of zero-shot (ablation)o3-mini · Task 1, 2 statementsoverall accuracy: 49.80% -> 51.70%Improved
add 3-shot examples with reasoning paths instead of zero-shot (ablation)gpt-5 · Task 2, 5 statementsexact accuracy: 0.073 -> 0.155Improved
add 3-shot examples with reasoning paths instead of zero-shot (ablation)gpt-5 · Task 2, 3 statementsexact accuracy: 0.439 -> 0.505Improved
restrict to short-reasoning-path samplesgpt-5 · Task 2 easy samplesexact accuracy: 34% -> 58%Improved
restrict to short-reasoning-path samplesgrok-4-fast · Task 2 easy samplesexact accuracy: 12% -> 31%Improved
restrict to short-statement-length samplesgpt-5 · Task 2 easy samplesexact accuracy: 34%No clear effect
evaluate on hard samples differing by one labelfrontier LLMs · Task 1 hard samplesaccuracy: around 80%Hurt
use counterfactual or commonsense propositionsLLMs · Task 2performanceNo clear effect
rewrite statements into human-style paraphrasessmall vs large LLMs · Task 2performanceMixed

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