2025/03/14 by Aïssatou Diallo, Antonis Bikakis, Diallo, Aissatou +7 · 2 citations
Computer Science · #Computation and Language (cs.CL) #Constructive #Control (management) #Corrective feedback #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Feedback loop #Flexibility (engineering) #Intelligent Tutoring Systems and Adaptive Learning #Iterative and incremental development #Language model #Language proficiency #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2503.11336
openalex publication_date 2025/03/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In this paper, we introduce Rule-Guided Feedback (RGF), a framework designed to enhance Large Language Model (LLM) performance through structured rule adherence and strategic information seeking. RGF implements a teacher-student paradigm where rule-following is forced through established guidelines. Our framework employs a Teacher model that rigorously evaluates each student output against task-specific rules, providing constructive guidance rather than direct answers when detecting deviations. This iterative feedback loop serves two crucial purposes: maintaining solutions within defined constraints and encouraging proactive information seeking to resolve uncertainties. We evaluate RGF on diverse tasks including Checkmate-in-One puzzles, Sonnet Writing, Penguins-In-a-Table classification, GSM8k, and StrategyQA. Our findings suggest that structured feedback mechanisms can significantly enhance LLMs' performance across various domains.