Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting

Jinwoo Ahn, Kyuseung ShinarXiv 2024 · DOI · arXiv

Introduction

When a Large Language Model (LLM) provides an incorrect response to a complex reasoning task, a common user reaction is to prompt the model to "try again" or "check your work." However, recent research suggests that this "redundant prompting"—repeatedly asking for a solution without providing specific guidance—can be counterproductive. This paper explores the phenomenon of performance degradation under repetitive feedback and introduces Recursive Chain-of-Feedback (R-CoF), a novel framework designed to help models self-correct by decomposing errors into manageable sub-problems.

The Divergence Trap in Redundant Prompting

The authors identify a significant issue termed the Chain-of-Feedback (CoF) effect. In standard interactions, providing meaningless or repetitive feedback often causes the model's performance to diverge further from the ground truth rather than converge upon it. As the number of trials increases, the model may hallucinate more wildly or eventually "give up," claiming no solution exists.

Figure 1: Deviation from the correct answer increases as the number of trials grows with redundant prompting.

To quantify this, the researchers developed a penalty function measuring the absolute deviation from correct numerical answers. If a model repeats an old error or fails to provide a solution, the penalty increases exponentially ($10 \times 2^n$). This metric highlights how standard iterative prompting fails to bridge the reliability gap for users who lack the expertise to verify complex reasoning steps themselves.

Methodology: Recursive Chain-of-Feedback (R-CoF)

To address this reliability gap, the authors propose Recursive Chain-of-Feedback (R-CoF). This method moves away from asking the model to re-evaluate the entire problem. Instead, it focuses on isolating and correcting specific failures within the reasoning chain.

The R-CoF process involves four key stages:

  1. Identify: Pinpoint the exact step where the reasoning logic failed.
  2. Isolate: Extract that specific incorrect step and transform it into a standalone, simplified sub-problem.
  3. Recursive Call: Query a separate LLM instance to solve only the isolated sub-problem, removing the distracting context of the original complex prompt.
  4. Integrate: Reinsert the corrected sub-step into the original reasoning chain to finalize the solution.
Figure 2: The R-CoF workflow isolates incorrect reasoning steps to generate a corrected final answer.

This approach effectively bypasses the "ignorance" problem, where models acknowledge a mistake but immediately repeat it because they are overwhelmed by the global context of the problem. By solving the step in a "clean" environment, the model's attention is focused, significantly increasing the likelihood of a correct calculation.

Experimental Results

The framework was evaluated using a subset of 50 difficult problems from the MATH dataset that ChatGPT-3.5 initially failed to solve. The results demonstrate the efficacy of the recursive approach:

  • Baseline: 0/50 (0% accuracy) using standard redundant prompting.
  • R-CoF (1 Recursive Call): Accuracy jumped to 31/50 (62%).
  • R-CoF (2 Recursive Calls): Accuracy reached 37/50 (74%).

These findings suggest that even a single level of recursive decomposition can resolve the majority of errors that previously led to total model failure.

Conclusion and Future Directions

While R-CoF significantly improves reasoning accuracy, it currently relies on manual identification of the incorrect reasoning step. Future work aims to automate this error-detection phase to create a fully autonomous self-correction loop. Additionally, expanding the testing to more advanced models and diverse domains such as code generation will be essential to understanding the broader applicability of recursive feedback mechanisms.

Summary updated

Abstract

Large Language Models (LLMs) frequently struggle with complex reasoning tasks, failing to construct logically sound steps towards the solution. In response to this behavior, users often try prompting the LLMs repeatedly in hopes of reaching a better response. This paper studies such repetitive behavior and its effect by defining a novel setting, Chain-of-Feedback (CoF). The setting takes questions that require multi-step reasoning as an input. Upon response, we repetitively prompt meaningless feedback (e.g. 'make another attempt') requesting additional trials. Surprisingly, our preliminary results show that repeated meaningless feedback gradually decreases the quality of the responses, eventually leading to a larger deviation from the intended outcome. To alleviate these troubles, we propose a novel method, Recursive Chain-of-Feedback (R-CoF). Following the logic of recursion in computer science, R-CoF recursively revises the initially incorrect response by breaking down each incorrect reasoning step into smaller individual problems. Our preliminary results show that majority of questions that LLMs fail to respond correctly can be answered using R-CoF without any sample data outlining the logical process.
BibTeX
@misc{ahn2024recursive,
  author = {Jinwoo Ahn and Kyuseung Shin},
  title = {{Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting}},
  year = {2024},
  eprint = {2402.02648},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.02648},
}
Figure