Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

• URL: http://arxiv.org/abs/2605.14561v1
• Date: Thu, 14 May 2026 08:33:47 GMT
• Title: Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations
• Abstract summary: 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.
• Score: 4.8833129337074626
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Prompt engineering is crucial for effective interaction with generative artificial intelligence systems, yet existing optimisation methods often operate over an unstructured and vast prompt space, leading to high computational costs and potential distortions of the original intent. We introduce Prompt Segmentation and Annotation Optimisation (PSAO), a structured prompt optimisation framework designed to improve prompt optimisation controllability and efficiency. PSAO decomposes a prompt into interpretable segments (e.g., sentences) and augments each with human-readable annotations (e.g., {not important}, {important}, {very important}). These annotations guide large language models (LLMs) in allocating focus and clarifying confusion during response generation. We formally define the segmentations and annotations and demonstrate that optimised segment-level annotations can lead to improved LLM responses, with the original prompt retained as a candidate in the optimisation space to prevent performance degradation. Empirical evaluations indicate that PSAO benefits from annotations in terms of improved reasoning accuracy and self-consistency. However, developing efficient methods for identifying optimal segmentations and annotations remains challenging and is reserved for future investigation. This work is intended as a proof of concept, demonstrating the feasibility and potential of segment-level annotation optimisation.

Related papers

• iPOE: Interpretable Prompt Optimization via Explanations [9.395538386620096]
  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.
  arXiv  Detail & Related papers  (2026-05-18T09:21:04Z)
• Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning [57.91658393667469]
  Interpretable Prompt Learning is a hybrid framework that alternates between discrete semantic token selection and continuous prompt optimization.<n>Our framework is plug-and-play, allowing seamless integration with existing prompt learning methods.
  arXiv  Detail & Related papers  (2026-05-06T02:38:59Z)
• Segment-Aligned Policy Optimization for Multi-Modal Reasoning [55.29606572822562]
  We propose a novel reinforcement learning paradigm that treats coherent reasoning steps, rather than tokens or full sequences as fundamental units of policy update.<n>Experiments on representative reasoning benchmarks demonstrate that SAPO consistently outperforms token-level and sequence-level policy optimization methods.<n>Our work underscores the importance of aligning reinforcement learning updates with the structure of reasoning, paving the way for more efficient and semantically grounded policy optimization in complex reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-02T08:47:45Z)
• Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning [0.0]
  Large Language Models (LLMs) have shown strong performance across a wide range of natural language processing tasks.<n>Their effectiveness is highly dependent on prompt design, structure, and embedded reasoning.<n>This paper presents a systematic study of DSPy-based declarative learning for prompt optimization.
  arXiv  Detail & Related papers  (2026-04-06T17:17:57Z)
• Automatic Prompt Optimization for Dataset-Level Feature Discovery [38.37728428959515]
  We formulate feature discovery as a dataset-level prompt optimization problem.<n>We propose a multi-agent prompt optimization framework in which language-model agents jointly propose feature definitions, extract feature values, and evaluate feature quality.<n>This formulation departs from prior prompt optimization methods that rely on per-sample supervision and provides a principled mechanism for automatic feature discovery from unstructured text.
  arXiv  Detail & Related papers  (2026-01-20T12:51:03Z)
• Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection [50.68751788132789]
  This study introduces an innovative methodology named as Weighted Semantic Map with Auto-adaptive Candidate Editing Network (WSAE-Net)<n>The generation of the weighted semantic map is designed to maximize the reduction of non-semantic feature units that need to be computed.<n>The auto-adaptive candidate editing sequences are designed to determine the optimal computational order among the feature units to be processed.
  arXiv  Detail & Related papers  (2025-11-17T05:34:10Z)
• AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation [113.75682363364004]
  AURORA is a framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation.<n>AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.
  arXiv  Detail & Related papers  (2025-08-04T07:47:38Z)
• POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation [8.946389785502861]
  Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses.<n>This paper introduces POPEN, a novel framework designed to address these issues and achieve improved results.
  arXiv  Detail & Related papers  (2025-04-01T10:51:01Z)
• 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)
• P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors [1.78761445544895]
  WeaklySupervised Semantic (WSSS) techniques explore individual regularization strategies to refine Class Activation Maps (CAMs) We devise two new techniques: P-NOC and CCAM-H. In the first, we promote the conjoint training of two adversarial CAM generating networks. In the latter, we employ the high quality pseudo-segmentation priors produced by P-NOC to guide the learning to saliency information in a weakly supervised fashion.
  arXiv  Detail & Related papers  (2023-05-21T17:46:28Z)
• FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment [93.09267863425492]
  We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable. We construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures.
  arXiv  Detail & Related papers  (2022-04-07T17:59:32Z)

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.