# Self-Review Framework for Enhancing Instruction Following Capability of LLM

arXiv: https://arxiv.org/abs/2507.05598 · HTML: https://mlsanity.com/paper/2507.05598/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 22 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models](https://mlsanity.com/paper/2310.20410/) (2023)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [COLLIE: Systematic Construction of Constrained Text Generation Tasks](https://mlsanity.com/paper/2307.08689/) (2023)
- [LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints](https://mlsanity.com/paper/2410.06458/) (2024)
- [Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints](https://mlsanity.com/paper/2302.09185/) (2023)
- [Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs](https://mlsanity.com/paper/2410.14641/) (2024)
- [Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?](https://mlsanity.com/paper/2410.12207/) (2024)

## Built on by (most cited first, 1 of 1)

- [Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment](https://mlsanity.com/paper/2512.04210/) (2025)

## Abstract (arXiv)

Various techniques have been proposed to improve large language models (LLMs) adherence to formatting and instruction constraints. One of the most effective approaches involves utilizing high-quality data generated by powerful models. However, such models often fail to fully comply with complex instructions in a single generation. To address this limitation, iterative revision methods have been introduced. Nevertheless, as the number of data points and revision iterations increases, the associated monetary costs grow significantly. As a resource-efficient alternative, methods have been proposed that leverage high-performance evaluation tools to compensate for the limited self-evaluation capabilities of open-source LLMs. However, these approaches often lead to a degradation in output quality due to excessive revision. To overcome these challenges, we propose Re5, a self-evaluation and revision framework designed to enhance instruction-following performance while preserving the quality of the generated content. Re5 extracts task and constraint components from user instructions, performs structural evaluations to prevent error accumulation, and applies fine-grained constraint-specific content evaluations followed by selective revisions. This process ensures precise and quality-preserving improvements. The final high-quality outputs are used for alignment tuning, enabling long-term alignment improvements through a data-centric iterative refinement loop. Experimental results demonstrate that Re5 achieves instruction-following performance comparable to models trained on data generated by GPT-4o-mini, a high-performance model, even with a small amount of data while maintaining response quality with a 64.24%-win rate over the non-revised initial responses. These results validate Re5 as an efficient and effective solution for enhancing instruction adherence with minimal external supervision.