Salvato in:
Dettagli Bibliografici
Autori principali: Diallo, Aissatou, Bikakis, Antonis, Dickens, Luke, Hunter, Anthony, Miller, Rob
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.11336
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916652672614400
author Diallo, Aissatou
Bikakis, Antonis
Dickens, Luke
Hunter, Anthony
Miller, Rob
author_facet Diallo, Aissatou
Bikakis, Antonis
Dickens, Luke
Hunter, Anthony
Miller, Rob
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models
Diallo, Aissatou
Bikakis, Antonis
Dickens, Luke
Hunter, Anthony
Miller, Rob
Computation and Language
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.
title Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2503.11336