paper-with-me

홈 › Papers

Prompt Selection Matters: Enhancing Text Annotations for Social Sciences with Large Language Models

2024-07-15 · Louis Abraham, Charles Arnal, Antoine Marie

Large Language Models have recently been applied to text annotation tasks from social sciences, equalling or surpassing the performance of human workers at a fraction of the cost. However, no inquiry has yet been made on the impact of prompt selection on labelling accuracy. In this study, we show that performance greatly varies between prompts, and we apply the method of automatic prompt optimization to systematically craft high quality prompts. We also provide the community with a simple, browser-based implementation of the method at https://prompt-ultra.github.io/ .

📄 PDF Abstract BibTeX arXiv:2407.10645

Code (0)

등록된 구현이 없습니다.

Tasks

text annotation

Similar Papers 제목 키워드 기반

Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways

2024-06-17 · Shubham Atreja, Joshua Ashkinaze, Lingyao Li, Julia Mendelsohn 외

Manually annotating data for computational social science tasks can be costly, time-consuming, and emotionally draining. While recent work suggests that LLMs can perform such annotation tasks in zero-shot settings, littl…

Model Selection

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

2025-10-08 · Ci-Siang Lin, Min-Hung Chen, I-Jieh Liu, Chien-Yi Wang 외 arxiv

Referring Video Object Segmentation (RVOS) aims to segment the object referred to by the query sentence in the video. Most existing methods require end-to-end training with dense mask annotations, which could be computat…

Referring Video Object Segmentation

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

2026-02-01 · Fu-Yun Wang, Han Zhang, Michael Gharbi, Hongsheng Li 외 arxiv

Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show…

Reinforcement LearningImage GenerationImage Editing

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning

2025-05-24 · Aofei Chang, Le Huang, Alex James Boyd, Parminder Bhatia 외

Medical Large Vision-Language Models (Med-LVLMs) often exhibit suboptimal attention distribution on visual inputs, leading to hallucinated or inaccurate outputs. Existing mitigation methods primarily rely on inference-ti…

Visual Question Answering (VQA)

Order Matters: Rethinking Prompt Construction in In-Context Learning

2025-11-12 · Warren Li, Yiqian Wang, Zihan Wang, Jingbo Shang arxiv

In-context learning (ICL) enables large language models to perform new tasks by conditioning on a sequence of examples. Most prior work reasonably and intuitively assumes that which examples are chosen has a far greater …