paper-with-me

홈 › Papers

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts

2025-05-19 · Chenyang Yang, Yike Shi, Qianou Ma, Michael Xieyang Liu, Christian Kästner, Tongshuang Wu

Building LLM-powered software requires developers to communicate their requirements through natural language, but developer prompts are frequently underspecified, failing to fully capture many user-important requirements. In this paper, we present an in-depth analysis of prompt underspecification, showing that while LLMs can often (41.1%) guess unspecified requirements by default, such behavior is less robust: Underspecified prompts are 2x more likely to regress over model or prompt changes, sometimes with accuracy drops by more than 20%. We then demonstrate that simply adding more requirements to a prompt does not reliably improve performance, due to LLMs' limited instruction-following capabilities and competing constraints, and standard prompt optimizers do not offer much help. To address this, we introduce novel requirements-aware prompt optimization mechanisms that can improve performance by 4.8% on average over baselines that naively specify everything in the prompt. Beyond prompt optimization, we envision that effectively managing prompt underspecification requires a broader process, including proactive requirements discovery, evaluation, and monitoring.

📄 PDF Abstract BibTeX arXiv:2505.13360

Code (1)

malusamayo/underspec-analysis 공식 구현

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification

2026-02-04 · Branislav Pecher, Michal Spiegel, Robert Belanec, Jan Cegin arxiv

Large language models (LLMs) are widely used as zero-shot and few-shot classifiers, where task behaviour is largely controlled through prompting. A growing number of works have observed that LLMs are sensitive to prompt …

Text Classification

Understanding the Impact of Negative Prompts: When and How Do They Take Effect?

2024-06-05 · Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Minhao Cheng 외

The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrating significant practical efficacy. Despi…

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation

2026-04-07 · Chengyi Yang, Pengzhen Li, Jiayin Qi, Aimin Zhou 외 arxiv

Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification o…

Text-to-Video GenerationVideo Alignment

Understanding the Multi-modal Prompts of the Pre-trained Vision-Language Model

2023-12-18 · Shuailei Ma, Chen-Wei Xie, Ying WEI, Siyang Sun 외

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. However, there is no work that provides a comprehensive explanation for the working…

Language ModelingLanguage ModellingPrompt Learning

DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

2022-10-26 · Zijie J. Wang, Evan Montoya, David Munechika, Haoyang Yang 외

With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often u…

DiversityMisinformation