TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

• URL: http://arxiv.org/abs/2605.21318v1
• Date: Wed, 20 May 2026 15:47:26 GMT
• Title: TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
• Abstract summary: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints.<n>We study this failure mode as prompt distributional overfitting and argue that it reflects a lack of representation control in discrete text-space optimization.<n>We propose TextReg, a regularization framework that realizes a soft-penalty objective through regularized textual gradients.
• Score: 41.70456027589437
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization methods iteratively rewrite prompts using LLM-generated feedback, but the resulting prompts often become longer, accumulate narrow sample-specific rules, and generalize poorly beyond the training distribution. We study this failure mode as prompt distributional overfitting and argue that it reflects a lack of representation control in discrete text-space optimization. We formalize this view through representational inefficiency, a dual-factor measure that decomposes prompt inefficiency into capacity cost and scope narrowness, attributing distributional prompt overfitting to their coupled growth during optimization. We propose TextReg, a regularization framework that realizes a soft-penalty objective through regularized textual gradients, combining Dual-Evidence Gradient Purification, Semantic Edit Regularization, and Regularization-Guided Prompt Update. Across multiple reasoning benchmarks, TextReg substantially improves out-of-distribution (OOD) generalization, with accuracy gains of up to +11.8% over TextGrad and +16.5% over REVOLVE.

Related papers

• GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer [51.31263673158136]
  GFlowPO casts prompt search as a posterior inference problem over latent prompts regularized by a meta-prompted reference-LM prior.<n>GFlowPO consistently outperforms recent discrete prompt optimization baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:30:03Z)
• Modular Prompt Optimization: Optimizing Structured Prompts with Section-Local Textual Gradients [0.8604557306886812]
  We introduce a schema-based prompt optimization framework that treats prompts as structured objects composed of fixed semantic sections.<n>We evaluate MPO on two reasoning benchmarks, ARC-Challenge and MMLU, using LLaMA-3 8B-Instruct and Mistral-7B-Instruct as solver models.
  arXiv  Detail & Related papers  (2026-01-07T16:20:08Z)
• RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling [59.088798018184235]
  textbfRAPO++ is a cross-stage prompt optimization framework.<n>It unifies training-data-aligned refinement, test-time iterative scaling, and large language model fine-tuning.<n> RAPO++ achieves significant gains in semantic alignment, compositional reasoning, temporal stability, and physical plausibility.
  arXiv  Detail & Related papers  (2025-10-23T04:45:09Z)
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution [0.0]
  We propose a framework that integrates a memory-augmented Reflection RetrievalRAG module and a Self-Adaptive meta-controller.<n>REMO achieves more stable and robust tuning, albeit at the cost of increased computational overhead.
  arXiv  Detail & Related papers  (2025-08-26T07:25:45Z)
• TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards [9.107586166322923]
  We introduce the Textual Reward Prompt framework (TRPrompt), which unifies approaches by incorporating textual feedback into training of the prompt model.<n>Our framework does not require prior dataset collection and is being iteratively improved with the feedback on the generated prompts.<n>When coupled with the capacity of an LLM to internalize the notion of what a "good" prompt is, the high-resolution signal provided by the textual rewards allows us to train a prompt model yielding state-of-the-art query-specific prompts.
  arXiv  Detail & Related papers  (2025-07-24T17:54:44Z)
• Fast Prompt Alignment for Text-to-Image Generation [28.66112701912297]
  This paper introduces Fast Prompt Alignment (FPA), a prompt optimization framework that leverages a one-pass approach.<n>FPA uses large language models (LLMs) for single-iteration prompt paraphrasing, followed by fine-tuning or in-context learning with optimized prompts.<n>FPA achieves competitive text-image alignment scores at a fraction of the processing time.
  arXiv  Detail & Related papers  (2024-12-11T18:58:41Z)
• 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)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)

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.