# Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models

arXiv: https://arxiv.org/abs/2503.11336 · HTML: https://mlsanity.com/paper/2503.11336/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [SoFA: Shielded On-the-fly Alignment via Priority Rule Following](https://mlsanity.com/paper/2402.17358/) (2024)
- [ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment](https://mlsanity.com/paper/2402.11000/) (2024)
- [Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems](https://mlsanity.com/paper/2305.11374/) (2023)

## Built on by (most cited first, 3 of 3)

- [RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling](https://mlsanity.com/paper/2506.08672/) (2025)
- [Sensory-Motor Control with Large Language Models via Iterative Policy Refinement](https://mlsanity.com/paper/2506.04867/) (2025)
- [Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models](https://mlsanity.com/paper/2607.14049/) (2026)

## Abstract (arXiv)

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.