中文
相关论文

相关论文: Comparative Evaluation of Prompting and Fine-Tunin…

200 篇论文

Prompt engineering is essential for optimizing large language models (LLMs), yet the link between prompt structures and task performance remains underexplored. This work introduces an evolutionary approach that combines context-free grammar…

计算与语言 · 计算机科学 2025-04-22 Gabriel Machado Santos , Rita Maria da Silva Julia , Marcelo Zanchetta do Nascimento

Large Language Models (LLMs) have been showing promising results for various NLP-tasks without the explicit need to be trained for these tasks by using few-shot or zero-shot prompting techniques. A common NLP-task is question-answering…

计算与语言 · 计算机科学 2024-12-18 Kevin Fischer , Darren Fürst , Sebastian Steindl , Jakob Lindner , Ulrich Schäfer

Large language models (LLMs) are increasingly adopted in educational technologies for a variety of tasks, from generating instructional materials and assisting with assessment design to tutoring. While prior work has investigated how models…

计算与语言 · 计算机科学 2025-12-24 Kirk Vanacore , Rene F. Kizilcec

Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when performing fine-grained visual editing. We introduce a…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Haoyu Zhen , Xiaolong Li , Yilin Zhao , Han Zhang , Sifei Liu , Kaichun Mo , Chuang Gan , Subhashree Radhakrishnan

Large language models (LLMs) have significantly advanced Natural Language Processing (NLP) tasks in recent years. However, their universal nature poses limitations in scenarios requiring personalized responses, such as recommendation…

计算与语言 · 计算机科学 2024-11-08 Stanisław Woźniak , Bartłomiej Koptyra , Arkadiusz Janz , Przemysław Kazienko , Jan Kocoń

We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning,…

计算与语言 · 计算机科学 2024-01-29 Chao-Han Huck Yang , Yile Gu , Yi-Chieh Liu , Shalini Ghosh , Ivan Bulyko , Andreas Stolcke

This paper explores the spatial reasoning capability of large language models (LLMs) over textual input through a suite of five tasks aimed at probing their spatial understanding and computational abilities. The models were tested on both…

计算与语言 · 计算机科学 2025-10-24 Maggie Bai , Ava Kim Cohen , Eleanor Koss , Charlie Lichtenbaum

Large language models (LLMs) can perform recommendation tasks by taking prompts written in natural language as input. Compared to traditional methods such as collaborative filtering, LLM-based recommendation offers advantages in handling…

信息检索 · 计算机科学 2025-07-21 Genki Kusano , Kosuke Akimoto , Kunihiro Takeoka

Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks. Previously, for zero-shot cross-lingual evaluation,…

计算与语言 · 计算机科学 2022-12-14 Lifu Tu , Caiming Xiong , Yingbo Zhou

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit natural language,…

计算与语言 · 计算机科学 2026-03-03 Xiaohe Bo , Rui Li , Zexu Sun , Quanyu Dai , Zeyu Zhang , Zihang Tian , Xu Chen , Zhenhua Dong

This paper describes the IUST NLP Lab submission to the Prompting Large Language Models as Explainable Metrics Shared Task at the Eval4NLP 2023 Workshop on Evaluation & Comparison of NLP Systems. We have proposed a zero-shot prompt-based…

计算与语言 · 计算机科学 2023-11-21 Ghazaleh Mahmoudi

Leveraging large language models (LLMs) for various natural language processing tasks has led to superlative claims about their performance. For the evaluation of machine translation (MT), existing research shows that LLMs are able to…

Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local…

人工智能 · 计算机科学 2025-08-07 Yanjie Dong , Haijun Zhang , Chengming Li , Song Guo , Victor C. M. Leung , Xiping Hu

Previous work has shown that there exists a scaling law between the size of Language Models (LMs) and their zero-shot performance on different downstream NLP tasks. In this work, we show that this phenomenon does not hold when evaluating…

计算与语言 · 计算机科学 2022-09-27 Joel Jang , Seonghyeon Ye , Minjoon Seo

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

计算与语言 · 计算机科学 2023-11-29 Utsav Garg , Erhan Bas

The remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on…

计算与语言 · 计算机科学 2023-09-26 Yinheng Li

Objective To develop soft prompt-based learning algorithms for large language models (LLMs), examine the shape of prompts, prompt-tuning using frozen/unfrozen LLMs, transfer learning, and few-shot learning abilities. Methods We developed a…

计算与语言 · 计算机科学 2024-04-16 Cheng Peng , Xi Yang , Kaleb E Smith , Zehao Yu , Aokun Chen , Jiang Bian , Yonghui Wu

Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex…

计算与语言 · 计算机科学 2026-03-06 Liang Yao

Large Language Models (LLMs) are trained on massive amounts of data, enabling their application across diverse domains and tasks. Despite their remarkable performance, most LLMs are developed and evaluated primarily in English. Recently, a…

计算与语言 · 计算机科学 2024-10-18 Krishno Dey , Prerona Tarannum , Md. Arid Hasan , Imran Razzak , Usman Naseem

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

计算与语言 · 计算机科学 2023-08-03 Zhiqiang Yuan , Junwei Liu , Qiancheng Zi , Mingwei Liu , Xin Peng , Yiling Lou