AI Paper Atlas

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

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

Huimin Ren, Yan Liang, Baiqiao Su, Chaobo Sun, Hengtong Lu, Kaike Zhang, Chen Wei

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 2 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
use reasoning-oriented models instead of non-reasoning counterpartsopen-source LLMs · LexInstructEvalstrict accuracy (%): Qwen2.5-72B 25.6 -> Qwen3-30B-A3B 36.2Improved
increase instruction difficulty from Easy to HardGPT-o3 · LexInstructEvalstrict accuracy (%): 82.4 -> 49.8Hurt
use loose instead of strict matchingGemini-2.5-Pro · LexInstructEvalaccuracy (%): 50.9 -> 59.1Improved
evaluate in English instead of ChineseGPT-o3 · LexInstructEvalstrict accuracy (%): 76.9 -> 63.5Hurt
increase procedure nesting depthGPT-o3 and DeepSeek-R1 · LexInstructEvalstrict accuracy (%)Hurt
scale Qwen2.5 from 7B to 72BQwen2.5 · LexInstructEvalstrict accuracy (%): 22.7 -> 25.6Improved

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