Rethinking Prompt Optimization: Reinforcement, Diversification, and Migration in Blackbox LLMs

• URL: http://arxiv.org/abs/2507.09839v1
• Date: Mon, 14 Jul 2025 00:20:14 GMT
• Title: Rethinking Prompt Optimization: Reinforcement, Diversification, and Migration in Blackbox LLMs
• Authors: MohammadReza Davari, Utkarsh Garg, Weixin Cai, Eugene Belilovsky,
• Abstract summary: We propose a novel Automatic Prompt Optimization (APO) framework centered on enhancing the feedback mechanism.<n>To mitigate the noise inherent in LLM-generated feedback, we introduce a technique called feedback diversification.<n>Our approach consistently outperforms strong baselines, achieving significant accuracy improvements, faster convergence, and lower computational costs.
• Score: 10.434732630519377
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model outputs. While recent Automatic Prompt Optimization (APO) methods iteratively refine prompts using model-generated feedback, textual gradients, they primarily focus on error correction and neglect valuable insights from correct predictions. This limits both their effectiveness and efficiency. In this paper, we propose a novel APO framework centered on enhancing the feedback mechanism. We reinterpret the textual gradient as a form of negative reinforcement and introduce the complementary positive reinforcement to explicitly preserve beneficial prompt components identified through successful predictions. To mitigate the noise inherent in LLM-generated feedback, we introduce a technique called feedback diversification, which aggregates multiple feedback signals, emphasizing consistent, actionable advice while filtering out outliers. Motivated by the rapid evolution and diversity of available LLMs, we also formalize Continual Prompt Optimization (CPO), addressing the practical challenge of efficiently migrating optimized prompts between different model versions or API providers. Our experiments reveal that naive prompt migration often degrades performance due to loss of critical instructions. In contrast, our approach consistently outperforms strong baselines, achieving significant accuracy improvements, faster convergence, and lower computational costs in both standard and migration scenarios.

Related papers

• Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? [41.69340422699651]
  This work investigates iterative approximate evaluation for arbitrary prompts.<n>It introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework.<n>MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced rollouts.
  arXiv  Detail & Related papers  (2025-07-07T03:20:52Z)
• Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent [24.134616865308985]
  We introduce a novel multi-turn preference optimization paradigm ECPO.<n>We show that ECPO significantly enhances CRA's interaction capabilities, delivering notable improvements in both efficiency and effectiveness over existing MTPO methods.
  arXiv  Detail & Related papers  (2025-06-17T08:29:04Z)
• Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
  We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization [59.39976343879587]
  VerIPO aims to gradually improve video LLMs' capacity for generating deep, long-term reasoning chains.<n>The training loop benefits from GRPO's expansive search and DPO's targeted optimization.<n>Our trained models exceed the direct inference of large-scale instruction-tuned Video-LLMs.
  arXiv  Detail & Related papers  (2025-05-25T06:41:28Z)
• Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining [66.54211199959298]
  We propose a novel preference learning framework, Modality-Balancing Preference Optimization (MBPO), to address the modality imbalance in LMMs.<n>MBPO constructs a more effective offline preference dataset by generating hard negatives, i.e., rejected responses misled by LLM biases.<n>It can enhance LMM performance on challenging vision-language tasks and effectively reduce hallucinations.
  arXiv  Detail & Related papers  (2025-05-20T03:59:05Z)
• Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization [29.706347050700867]
  Large Video Language Models (LVLMs) struggle with fine-grained temporal understanding, hallucinate, and often make simple mistakes on even simple video question-answering tasks.<n>We propose a self-alignment framework that enables LVLMs to learn from their own errors.
  arXiv  Detail & Related papers  (2025-04-16T13:43:56Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
  We introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
  arXiv  Detail & Related papers  (2024-05-26T00:29:04Z)
• Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers [108.72225067368592]
  We propose a novel perspective to investigate the design of large language models (LLMs)-based prompts.<n>We identify two pivotal factors in model parameter learning: update direction and update method.<n>We develop a capable Gradient-inspired Prompt-based GPO.
  arXiv  Detail & Related papers  (2024-02-27T15:05:32Z)
• Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game [31.66896160733569]
  We propose an Adversarial Preference Optimization (APO) framework to target more efficient human preference optimization. We find the proposed adversarial training framework further enhances existing alignment baselines in terms of LLM helpfulness and harmlessness.
  arXiv  Detail & Related papers  (2023-11-14T10:10:31Z)
• PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine [24.888093229577965]
  We propose a simple, universal, and automatic method named PREFER to address the stated limitations. Our PREFER achieves state-of-the-art performance in multiple types of tasks by a significant margin.
  arXiv  Detail & Related papers  (2023-08-23T09:46:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.