PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models

• URL: http://arxiv.org/abs/2505.16307v2
• Date: Thu, 18 Sep 2025 16:37:35 GMT
• Title: PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
• Authors: Chenzhuo Zhao, Ziqian Liu, Xinda Wang, Junting Lu, Chaoyi Ruan,
• Abstract summary: PMPO locates low quality prompt segments via a masking based analysis and iteratively rewrites them to propose improved variants.<n>It selects among variants by minimizing loss in a single forward pass, eliminating output sampling and human or judge based scoring for selection.<n>Across model sizes and datasets, PMPO outperforms prior prompts: it achieves the highest average accuracy on BBH, performs strongly on GSM8K and AQUA RAT, and raises AlpacaEval 2.0 win rates by over 19 points.
• Score: 1.6816171955882597
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate prompts by sampling full outputs, often coupled with self critique or human annotated preferences, which limits scalability, especially for smaller models or models that are not instruction tuned. We present PMPO (Probabilistic Metric Prompt Optimization), a unified framework that uses token level cross entropy as a direct, lightweight evaluation signal. PMPO locates low quality prompt segments via a masking based analysis and iteratively rewrites them to propose improved variants. Crucially, during evaluation, PMPO selects among variants by minimizing loss in a single forward pass, eliminating output sampling and human or judge based scoring for selection while still using standard generation only to propose rewrites. This unified, loss based strategy supports both supervised and preference based tasks. Across model sizes and datasets, PMPO outperforms prior prompt optimizers: it achieves the highest average accuracy on BBH, performs strongly on GSM8K and AQUA RAT, and raises AlpacaEval 2.0 win rates by over 19 points. These results demonstrate PMPO's effectiveness, efficiency, and broad applicability.

Related papers

• SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization [64.95852289011385]
  Large language models (LLMs) continue to scale up, their performance on various downstream tasks has significantly improved.<n> evaluating their capabilities has become increasingly expensive, as performing inference on a large number of benchmark samples incurs high computational costs.<n>We propose SparseEval, a method that, for the first time, adopts gradient descent to optimize anchor weights and employs an iterative refinement strategy for anchor selection.
  arXiv  Detail & Related papers  (2026-02-08T11:12:45Z)
• Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains [67.71020482405343]
  We study how to design algorithms that can leverage additional information in the form of rating gap.<n>We present new algorithms that can achieve faster statistical rates than DPO in presence of accurate rating gap information.
  arXiv  Detail & Related papers  (2026-01-31T08:38:21Z)
• Offline Preference Optimization via Maximum Marginal Likelihood Estimation [9.001971182501501]
  This work recasts alignment through the lens of Marginal Likelihood estimation.<n>Our new MML based Preference Optimization (MMPO) maximizes the marginal log-likelihood of a preferred text output.<n>We show that MMPO achieves competitive or superior preference alignment while better preserving the base model's general language capabilities.
  arXiv  Detail & Related papers  (2025-10-27T00:15:57Z)
• On the Role of Preference Variance in Preference Optimization [55.364953481473286]
  We investigate the impact of emphpreference variance (PVar) on the effectiveness of Direct Preference Optimization (DPO) training.<n>We show that prompts with higher PVar outperform randomly selected prompts or those with lower PVar.
  arXiv  Detail & Related papers  (2025-10-14T22:34:52Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [58.651951388346525]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>Our results show that diffusion models fine-tuned with DMPO can consistently outperform or match existing techniques.<n>DMPO unlocks a robust and elegant pathway for preference alignment, bridging principled theory with practical performance in diffusion models.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? [65.18157595903124]
  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)
• Adaptive Sample Scheduling for Direct Preference Optimization [37.75208455935495]
  We introduce a novel problem: Sample Scheduling for DPO.<n>It aims to dynamically and adaptively schedule training samples based on the model's evolving states.<n>We propose SamS, an efficient and effective algorithm that adaptively selects samples in each training batch.
  arXiv  Detail & Related papers  (2025-06-08T10:26:09Z)
• Improved Methods for Model Pruning and Knowledge Distillation [3.8993503758122663]
  MAMA Pruning is a performance optimization technique for large language models like R1 or o3-mini.<n>It effectively reduces model size and computational complexity while maintaining performance comparable to the original unpruned model even at extreme pruned levels.<n>Preliminary experimental results show that our method outperforms and be comparable to state-of-the-art methods across various pruning levels and different downstream computational linguistics tasks.
  arXiv  Detail & Related papers  (2025-05-20T07:53:40Z)
• Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization [12.683042228674694]
  IPOMP is a two-stage approach that selects representative and diverse samples using semantic clustering and boundary analysis.<n>We show that IPOMP improves effectiveness by 1.6% to 5.3% and stability by at least 57% compared with SOTA baselines.
  arXiv  Detail & Related papers  (2025-05-15T22:41:30Z)
• Sample, Don't Search: Rethinking Test-Time Alignment for Language Models [55.2480439325792]
  We introduce QAlign, a new test-time alignment approach.<n>As we scale test-time compute, QAlign converges to sampling from the optimal aligned distribution for each individual prompt.<n>By adopting recent advances in Markov chain Monte Carlo for text generation, our method enables better-aligned outputs without modifying the underlying model or even requiring logit access.
  arXiv  Detail & Related papers  (2025-04-04T00:41:40Z)
• A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning [61.403275660120606]
  Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives.<n>We propose leave-one-out PPO (LOOP), a novel RL for diffusion fine-tuning method.<n>Our results demonstrate that LOOP effectively improves diffusion models on various black-box objectives, and achieves a better balance between computational efficiency and performance.
  arXiv  Detail & Related papers  (2025-03-02T13:43:53Z)
• Length-Controlled Margin-Based Preference Optimization without Reference Model [11.878496378814045]
  We propose Length-Controlled Margin-Based Preference Optimization (LMPO) for preference-based reinforcement learning.<n>A key innovation of LMPO lies in its Length-Controlled Margin-Based loss function, integrated within the Bradley-Terry framework.<n>Our experimental results demonstrate that LMPO effectively controls response length, reduces probability degradation, and outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-02-20T15:30:27Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.<n>In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.<n> DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Understanding Likelihood Over-optimisation in Direct Alignment Algorithms [20.043560907227018]
  Direct Alignment Algorithms (DAAs) have emerged as alternatives to online Reinforcement Learning from Human Feedback. These algorithms aim to increase the likelihood of generating better (preferred) completions while discouraging worse (non-preferred) ones. This work explores the relationship between completion likelihood and model performance in state-of-the-art DAAs.
  arXiv  Detail & Related papers  (2024-10-15T15:14:22Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.