中文
相关论文

相关论文: Why Prompt Optimization Works, and Why It Sometime…

200 篇论文

Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating interpretable prompts and being compatible with black-box…

机器学习 · 计算机科学 2023-10-26 Dong-Ki Kim , Sungryull Sohn , Lajanugen Logeswaran , Dongsub Shim , Honglak Lee

Large Language Models (LLMs) have gained widespread popularity due to their ability to perform ad-hoc Natural Language Processing (NLP) tasks with a simple natural language prompt. Part of the appeal for LLMs is their approachability to the…

人机交互 · 计算机科学 2025-02-25 Aditi Mishra , Utkarsh Soni , Anjana Arunkumar , Jinbin Huang , Bum Chul Kwon , Chris Bryan

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

计算与语言 · 计算机科学 2024-03-08 Rui Wang , Hongru Wang , Fei Mi , Yi Chen , Boyang Xue , Kam-Fai Wong , Ruifeng Xu

Large Language Models (LLMs) have shown remarkable capabilities in manipulating natural language across multiple applications, but their ability to handle simple reasoning tasks is often questioned. In this work, we aim to provide a…

计算与语言 · 计算机科学 2025-05-05 Alessandro Raganato , Rafael Peñaloza , Marco Viviani , Gabriella Pasi

In Large Language Models (LLMs), there have been consistent advancements in task-specific performance, largely influenced by effective prompt design. Recent advancements in prompting have enhanced reasoning in logic-intensive tasks for…

计算与语言 · 计算机科学 2024-03-22 Yuqing Wang , Yun Zhao

Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform exact, deterministic computation remains unclear. In this work, we systematically evaluate…

人工智能 · 计算机科学 2026-05-08 Hongkun Yu

Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An attempt to automate…

计算与语言 · 计算机科学 2023-06-26 Yulin Zhou , Yiren Zhao , Ilia Shumailov , Robert Mullins , Yarin Gal

Prompting has shown impressive success in enabling large pretrained language models (LMs) to perform diverse NLP tasks, especially when only few downstream data are available. Automatically finding the optimal prompt for each task, however,…

计算与语言 · 计算机科学 2022-10-25 Mingkai Deng , Jianyu Wang , Cheng-Ping Hsieh , Yihan Wang , Han Guo , Tianmin Shu , Meng Song , Eric P. Xing , Zhiting Hu

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization…

机器学习 · 计算机科学 2025-11-18 Fei Song , Yi Li , Rui Wang , Jiahuan Zhou , Changwen Zheng , Jiangmeng Li

Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to assess whether system code implementation…

软件工程 · 计算机科学 2025-08-19 Haolin Jin , Huaming Chen

Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…

计算与语言 · 计算机科学 2024-08-15 Dai Do , Quan Tran , Svetha Venkatesh , Hung Le

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

机器学习 · 计算机科学 2026-01-14 Andrew Zhao , Reshmi Ghosh , Vitor Carvalho , Emily Lawton , Keegan Hines , Gao Huang , Jack W. Stokes

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

计算与语言 · 计算机科学 2025-04-01 Sid Bharthulwar , John Rho , Katrina Brown

Batch prompting is a common technique in large language models (LLMs) used to process multiple inputs simultaneously, aiming to improve computational efficiency. However, as batch sizes increase, performance degradation often occurs due to…

计算与语言 · 计算机科学 2024-10-03 Longyu Feng , Mengze Hong , Chen Jason Zhang

Large language models (LLMs) enable strong text generation, and in general there is a practical tradeoff between fine-tuning and prompt engineering. We introduce Simplify-This, a comparative study evaluating both paradigms for text…

计算与语言 · 计算机科学 2026-01-12 Eilam Cohen , Itamar Bul , Danielle Inbar , Omri Loewenbach

Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing…

人工智能 · 计算机科学 2025-11-26 Ke Chen , Yifeng Wang , Hassan Almosapeeh , Haohan Wang

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

计算与语言 · 计算机科学 2024-03-28 Jean Ghislain Billa , Min Oh , Liang Du

Existing efforts to improve logical reasoning ability of language models have predominantly relied on supervised fine-tuning, hindering generalization to new domains and/or tasks. The development of Large Langauge Models (LLMs) has…

计算与语言 · 计算机科学 2024-06-18 Fangkai Jiao , Zhiyang Teng , Bosheng Ding , Zhengyuan Liu , Nancy F. Chen , Shafiq Joty

We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) inspired by human meta-reasoning. Traditional in-context learning-based reasoning techniques, such as…

计算与语言 · 计算机科学 2024-06-18 Peizhong Gao , Ao Xie , Shaoguang Mao , Wenshan Wu , Yan Xia , Haipeng Mi , Furu Wei

Requirements classification assigns natural language requirements to predefined classes, such as functional and non functional. Accurate classification reduces risk and improves software quality. Most existing models rely on supervised…

软件工程 · 计算机科学 2025-09-18 Manal Binkhonain , Reem Alfayaz