中文
相关论文

相关论文: The Geometry of Prompting: Unveiling Distinct Mech…

200 篇论文

In recent years, Large Language Models have garnered significant attention for their strong performance in various natural language tasks, such as machine translation and question answering. These models demonstrate an impressive ability to…

计算与语言 · 计算机科学 2025-02-21 Qibang Liu , Wenzhe Wang , Jeffrey Willard

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…

Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into geometrical relationships between their vector…

计算与语言 · 计算机科学 2025-05-26 Raphaël Sarfati , Haley Moller , Toni J. B. Liu , Nicolas Boullé , Christopher Earls

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

计算与语言 · 计算机科学 2026-02-17 Jan Philip Wahle , Terry Ruas , Yang Xu , Bela Gipp

Prompting is a mainstream paradigm for adapting large language models to specific natural language processing tasks without modifying internal parameters. Therefore, detailed supplementary knowledge needs to be integrated into external…

计算与语言 · 计算机科学 2024-12-03 Kaiyan Chang , Songcheng Xu , Chenglong Wang , Yingfeng Luo , Xiaoqian Liu , Tong Xiao , Jingbo Zhu

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

音频与语音处理 · 电气工程与系统科学 2024-08-26 Kai-Wei Chang , Haibin Wu , Yu-Kai Wang , Yuan-Kuei Wu , Hua Shen , Wei-Cheng Tseng , Iu-thing Kang , Shang-Wen Li , Hung-yi Lee

Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language models (VLMs). This approach leverages task-specific instructions, known as prompts, to enhance…

人工智能 · 计算机科学 2025-03-18 Pranab Sahoo , Ayush Kumar Singh , Sriparna Saha , Vinija Jain , Samrat Mondal , Aman Chadha

Prompt engineering has emerged as a powerful technique for guiding large language models (LLMs) toward desired responses, significantly enhancing their performance across diverse tasks. Beyond their role as static predictors, LLMs…

机器学习 · 计算机科学 2025-03-27 Ryumei Nakada , Wenlong Ji , Tianxi Cai , James Zou , Linjun Zhang

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…

计算与语言 · 计算机科学 2024-09-16 Hila Gonen , Srini Iyer , Terra Blevins , Noah A. Smith , Luke Zettlemoyer

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

计算与语言 · 计算机科学 2024-06-25 Allmin Balloccu , Jack Zhang

Despite the remarkable successes of large language models (LLMs), the underlying Transformer architecture has inherent limitations in handling complex reasoning tasks. Chain-of-thought (CoT) prompting has emerged as a practical workaround,…

计算与语言 · 计算机科学 2025-06-03 Xiang Zhang , Juntai Cao , Jiaqi Wei , Chenyu You , Dujian Ding

Recent work has shown that prompting language models with code-like representations of natural language leads to performance improvements on structured reasoning tasks. However, such tasks comprise only a small subset of all natural…

计算与语言 · 计算机科学 2023-04-27 Li Zhang , Liam Dugan , Hainiu Xu , Chris Callison-Burch

Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic…

计算与语言 · 计算机科学 2023-10-25 Corentin Kervadec , Francesca Franzon , Marco Baroni

Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-text prompting strategies. To solve this, we introduce a…

计算与语言 · 计算机科学 2025-11-07 Ercong Nie , Shuzhou Yuan , Bolei Ma , Helmut Schmid , Michael Färber , Frauke Kreuter , Hinrich Schütze

Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts…

机器学习 · 计算机科学 2026-05-05 Dongseok Kim , Hyoungsun Choi , Mohamed Jismy Aashik Rasool , Gisung Oh

There have been many recent investigations into prompt-based training of transformer language models for new text genres in low-resource settings. The prompt-based training approach has been found to be effective in generalizing pre-trained…

计算与语言 · 计算机科学 2023-06-13 Jennifer D'Souza , Moussab Hrou , Sören Auer

Prompt engineering is a technique that involves augmenting a large pre-trained model with task-specific hints, known as prompts, to adapt the model to new tasks. Prompts can be created manually as natural language instructions or generated…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Jindong Gu , Zhen Han , Shuo Chen , Ahmad Beirami , Bailan He , Gengyuan Zhang , Ruotong Liao , Yao Qin , Volker Tresp , Philip Torr

We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning. While prompting is often favored for its parameter efficiency and flexibility, it…

人工智能 · 计算机科学 2025-06-26 Rahul Raja , Arpita Vats

Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifying the best-performing LLM for a given task is a significant…

计算与语言 · 计算机科学 2025-11-13 Idan Kashani , Avi Mendelson , Yaniv Nemcovsky

Demonstrations and instructions are two primary approaches for prompting language models to perform in-context learning (ICL) tasks. Do identical tasks elicited in different ways result in similar representations of the task? An improved…

计算与语言 · 计算机科学 2025-12-02 Guy Davidson , Todd M. Gureckis , Brenden M. Lake , Adina Williams
‹ 上一页 1 2 3 10 下一页 ›