AI Paper Atlas

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

RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models

Yang Yang, Hua XU, Zhangyi Hu, Yutao Yue

ICML 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation · 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
use logistic combiner instead of prompting with rules (E2) (ablation)RLIE (DeepSeek-V3.2) · Citationsaccuracy: 60.4 -> 64.6Improved
use logistic combiner instead of prompting with rules (E2) (ablation)RLIE (DeepSeek-V3.2) · Reviewsaccuracy: 65.7 -> 70.9Improved
add rule weights to the LLM prompt (E3 vs E2) (ablation)RLIE rules · 6 datasets, DeepSeek-V3.2accuracy: LLM Detect 89.6 -> 85.2; Citations 60.4 -> 55.2Hurt
add combiner prediction to the prompt (E4 vs E3) (ablation)RLIE rules · Reviews, DeepSeek-V3.2accuracy: 65.4 -> 69.5Improved
add combiner prediction to the prompt (E4 vs E3) (ablation)RLIE rules · Citations, DeepSeek-V3.2accuracy: 55.2 -> 57.3 (still below combiner 64.6)Mixed
use stronger backbone (DeepSeek-V3.2 vs Qwen3-Next-80B)RLIE · LLM Detectaccuracy: 87.6 -> 90.7Improved
iterative multi-rule weighted RLIE vs single-rule IO RefinementRLIE · Headlinesaccuracy: 62.0 -> 67.0Improved
add multiple rules without global weights (HypoGeniC) vs single-rule IO RefinementHypoGeniC · Headlinesaccuracy: 62.0 -> 59.9No clear effect
few-shot examples vs zero-shotDeepSeek-V3.2 · Retweetsaccuracy: 63.5 -> 57.7Hurt
hard-example driven refinement vs maintaining large rule bankRLIE vs HypoGeniC · token costavg tokens (M): 13.24 -> 12.23Improved
L1 regularization prunes uninformative rulesRLIE · Headlines rule setrule weight: Urgency rule weight 0.000Improved

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