AI Paper Atlas

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

ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions

Xingwei He, Qianru Zhang, Pengfei Chen, Guanhua Chen, Linlin Yu, Yuan Yuan, Siu-Ming Yiu

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 5 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 the guiding prompt for Behavior 2GPT-4o · ConInstruct, one conflict% unacknowledged (B1): 97 -> 4Improved
add the guiding prompt for Behavior 2GPT-4o · ConInstruct, conflict-free instructions% unnecessary clarification (B6): 0 -> 40Hurt
add the guiding prompt for Behavior 2GPT-4o-mini · ConInstruct, conflict-free instructions% unnecessary clarification (B6): 0 -> 53Hurt
add the guiding prompt for Behavior 2Claude-3.5-Sonnet · ConInstruct, one conflict% unacknowledged (B1): 78 -> 18Improved
add the guiding prompt for Behavior 2Claude-3.5-Haiku · ConInstruct, one conflict% unacknowledged (B1): 93 -> 16Improved
increase number of conflicts from 1-2 to 5-6Claude-3.5-Sonnet · ConInstruct conflict resolution% acknowledging conflicts (B2+B3): 32.0% -> 64.0%Improved
inter-constraint instead of intra-constraint conflictsClaude-3.5-Sonnet · ConInstruct conflict detectionF1: 92.7 -> 74.6Hurt
increase model size from 7B to 14BQwen2.5-Instruct · ConInstruct conflict detectionaverage F1: 57.9 -> 75.8Improved
increase model size from 14B to 32BQwen2.5-Instruct · ConInstruct conflict detectionaverage F1: 75.8 -> 74.1No clear effect
add a newly introduced conflicting constraintLLMs · ConInstruct (CC, KK, PP conflicts)original-constraint satisfaction rateHurt
place the new conflicting constraint before the original constraintLLMs · ConInstruct (CC, KK, PP conflicts)original-constraint satisfaction rateImproved

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