iPOE: Interpretable Prompt Optimization via Explanations

• URL: http://arxiv.org/abs/2605.18113v2
• Date: Wed, 27 May 2026 11:07:32 GMT
• Title: iPOE: Interpretable Prompt Optimization via Explanations
• Abstract summary: We introduce iPOE, a novel interpretable prompt optimization strategy via explanations.<n>We find that iPOE can improve over the evaluated baselines by up to 39% and LLM explanations can replace human explanations.
• Score: 9.395538386620096
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Prompt optimization has often been framed as a discrete search problem to find high-performing and robust instructions for an LLM. However, the search result might not make it transparent why and where specific prompt changes lead to performance gains. This is in contrast to how humans are instructed for annotation tasks. Here, researchers carefully design annotation guidelines, leading to enhanced annotation consistency. Our paper aims at joining these two approaches and introduces iPOE, a novel interpretable prompt optimization strategy via explanations. We guide the prompt optimization process by automatically created guidelines from explanations of annotation decisions (either automatically generated or from humans). This set of guidelines is furthermore optimized by as series of operations, including removing, adding, shuffling, and merging. The resulting prompt includes guidelines that instruct the annotation, making the decision process of the LLM and the optimization transparent. It therefore supports also laypeople in the area of prompt optimization, particularly in challenging domains requiring expertise. In our experiments on four datasets, we find that iPOE can improves over the evaluated baselines by up to 39% and LLM explanations can replace human explanations in the proposed method. Moreover, our interpretability validation study demonstrates that humans and LLMs can substantially agree on which guidelines contribute to their annotations, achieving a Cohen's kappa score of up to 0.65.

Related papers

• Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations [4.8833129337074626]
  We introduce Prompt and optimisation (PSAO), a structured prompt optimisation framework to improve controllability and efficiency.<n>PSAO decomposes a prompt into interpretable segments (e.g., sentences) and augments each with human-readable annotations.<n>These annotations guide large language models (LLMs) in allocating focus and clarifying confusion during response generation.
  arXiv  Detail & Related papers  (2026-05-14T08:33:47Z)
• Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt [13.863963355859175]
  We propose a pre-inference prompt optimization mechanism via explicit prompt disambiguation.<n>We identify semantic risks in the prompt, check their multi-perspective consistency, and resolve any semantic conflicts.<n>Our method improves reasoning performance by 2.5 points at a cost of only $0.02.
  arXiv  Detail & Related papers  (2026-04-25T12:13:26Z)
• Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting [2.743338598862049]
  We investigate how LLM-based rewriting of advertisements can improve their ranking in retrieval systems.<n>We introduce a supervised fine-tuning framework with a custom loss balancing semantic relevance and content fidelity.
  arXiv  Detail & Related papers  (2025-07-03T05:36:08Z)
• Rethinking Prompt Optimizers: From Prompt Merits to Optimization [14.01541576309104]
  MePO is a merit-guided, locally deployable prompt trained on a merit-guided prompt dataset.<n>MePO avoids online optimization, reduces privacy concerns, and, by learning clear, interpretable merits, generalizes effectively to both large-scale and lightweight inference models.
  arXiv  Detail & Related papers  (2025-05-15T03:31:37Z)
• Meta-Prompt Optimization for LLM-Based Sequential Decision Making [24.050701239196876]
  Large language models (LLMs) have been employed as agents to solve sequential decision-making tasks.<n>We propose our EXPonential-weight algorithm for prompt Optimization (EXPO) to automatically optimize the task description and meta-instruction in the meta-prompt.<n>We also extend EXPO to additionally optimize the exemplars in the meta-prompt to further enhance the performance.
  arXiv  Detail & Related papers  (2025-02-02T09:22:39Z)
• IPO: Interpretable Prompt Optimization for Vision-Language Models [40.83071220530289]
  This paper introduces a simple but interpretable prompt (IPO) IPO utilizes large language models (LLMs) to generate textual prompts dynamically. We incorporate a large multimodal model (LMM) to condition on visual content by generating image descriptions.
  arXiv  Detail & Related papers  (2024-10-20T14:10:22Z)
• 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)
• MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization [73.7779735046424]
  We show that different prompts should be adapted to different Large Language Models (LLM) to enhance their capabilities across various downstream tasks in NLP. We then propose a model-adaptive prompt (MAPO) method that optimize the original prompts for each specific LLM in downstream tasks.
  arXiv  Detail & Related papers  (2024-07-04T18:39:59Z)
• Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement [11.363521189714504]
  We show that large language models (LLMs) are over-sensitive to lexical variations in task instructions. We propose a black-box Combinatorial Optimization framework for Prompt Lexical Enhancement (COPLE)
  arXiv  Detail & Related papers  (2024-05-31T08:53:59Z)
• Efficient Prompting Methods for Large Language Models: A Survey [50.82812214830023]
  Efficient Prompting Methods have attracted a wide range of attention.<n>We discuss Automatic Prompt Engineering for different prompt components and Prompt Compression in continuous and discrete spaces.
  arXiv  Detail & Related papers  (2024-04-01T12:19:08Z)
• PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling [20.0605311279483]
  We introduce PRompt Optimization in Multi-Step Tasks (PROMST) It incorporates human-designed feedback rules to automatically offer direct suggestions for improvement. It significantly outperforms both human-engineered prompts and several other prompt optimization methods across 11 representative multi-step tasks.
  arXiv  Detail & Related papers  (2024-02-13T16:38:01Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• Prompt-Tuning Decision Transformer with Preference Ranking [83.76329715043205]
  We propose the Prompt-Tuning DT algorithm to address challenges by using trajectory segments as prompts to guide RL agents in acquiring environmental information. Our approach involves randomly sampling a Gaussian distribution to fine-tune the elements of the prompt trajectory and using preference ranking function to find the optimization direction. Our work contributes to the advancement of prompt-tuning approaches in RL, providing a promising direction for optimizing large RL agents for specific preference tasks.
  arXiv  Detail & Related papers  (2023-05-16T17:49:04Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• 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.