中文
相关论文

相关论文: Towards LLMs Robustness to Changes in Prompt Forma…

200 篇论文

Large Multimodal Models (LMMs) exhibit remarkable multi-tasking ability by learning mixed instruction datasets. However, novel tasks would be encountered sequentially in dynamic world, which urges for equipping LMMs with multimodal…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Fanhu Zeng , Fei Zhu , Haiyang Guo , Xu-Yao Zhang , Cheng-Lin Liu

Large Language models (LLMs) have emerged as powerful tools for addressing challenges across diverse domains. Notably, recent studies have demonstrated that large language models significantly enhance the efficiency of biomolecular analysis…

计算与语言 · 计算机科学 2025-03-07 Jiyue Jiang , Zikang Wang , Yuheng Shan , Heyan Chai , Jiayi Li , Zixian Ma , Xinrui Zhang , Yu Li

Large Vision-Language Models (LVLMs) have exhibited impressive capabilities across various visual tasks, yet they remain hindered by the persistent challenge of hallucinations. To address this critical issue, we propose Mixture of Decoding…

计算与语言 · 计算机科学 2025-06-11 Xinlong Chen , Yuanxing Zhang , Qiang Liu , Junfei Wu , Fuzheng Zhang , Tieniu Tan

Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Yongzhu Miao , Shasha Li , Jintao Tang , Ting Wang

Using large language models (LLMs) for source code has recently gained attention. LLMs, such as Transformer-based models like Codex and ChatGPT, have been shown to be highly capable of solving a wide range of programming problems. However,…

计算与语言 · 计算机科学 2023-06-27 Atsushi Shirafuji , Yutaka Watanobe , Takumi Ito , Makoto Morishita , Yuki Nakamura , Yusuke Oda , Jun Suzuki

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

计算与语言 · 计算机科学 2026-02-04 Patrick Cooper , Alireza Nadali , Ashutosh Trivedi , Alvaro Velasquez

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

计算与语言 · 计算机科学 2025-06-04 Edoardo Cetin , Tianyu Zhao , Yujin Tang

The wording of natural language prompts has been shown to influence the performance of large language models (LLMs), yet the role of politeness and tone remains underexplored. In this study, we investigate how varying levels of prompt…

计算与语言 · 计算机科学 2025-10-07 Om Dobariya , Akhil Kumar

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

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer,…

机器学习 · 计算机科学 2024-12-30 Pei-Fu Guo , Yun-Da Tsai , Shou-De Lin

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

人机交互 · 计算机科学 2026-03-26 Minjae Lee , Minsuk Kahng

Despite their remarkable capabilities, Large Language Models (LLMs) are found to be surprisingly sensitive to minor variations in prompts, often generating significantly divergent outputs in response to minor variations in the prompts, such…

计算与语言 · 计算机科学 2024-10-07 Anwoy Chatterjee , H S V N S Kowndinya Renduchintala , Sumit Bhatia , Tanmoy Chakraborty

Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms…

计算与语言 · 计算机科学 2025-07-28 Rithesh Murthy , Ming Zhu , Liangwei Yang , Jielin Qiu , Juntao Tan , Shelby Heinecke , Caiming Xiong , Silvio Savarese , Huan Wang

While Large Language Models (LLMs) are being quickly adapted to many domains, including healthcare, their strengths and pitfalls remain under-explored. In our study, we examine the effects of prompt engineering to guide Large Language…

计算与语言 · 计算机科学 2024-09-04 Daniil Filienko , Yinzhou Wang , Caroline El Jazmi , Serena Xie , Trevor Cohen , Martine De Cock , Weichao Yuwen

The performance of large language models (LLMs) is significantly influenced by the quality of the prompts provided. In response, researchers have developed enormous prompt engineering strategies aimed at modifying the prompt text to enhance…

计算与语言 · 计算机科学 2024-10-23 Zhiyuan He , Huiqiang Jiang , Zilong Wang , Yuqing Yang , Luna Qiu , Lili Qiu

Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple…

Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. Among the myriad of applications that benefit from LLMs, automated code generation is increasingly promising. The…

软件工程 · 计算机科学 2023-11-15 Lincoln Murr , Morgan Grainger , David Gao

Finding the best way of adapting pre-trained language models to a task is a big challenge in current NLP. Just like the previous generation of task-tuned models (TT), models that are adapted to tasks via in-context-learning (ICL) are robust…

计算与语言 · 计算机科学 2023-10-23 Lucas Weber , Elia Bruni , Dieuwke Hupkes

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

计算与语言 · 计算机科学 2024-05-31 Xudong Lu , Qi Liu , Yuhui Xu , Aojun Zhou , Siyuan Huang , Bo Zhang , Junchi Yan , Hongsheng Li

Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt…

计算与语言 · 计算机科学 2024-02-06 Moxin Li , Wenjie Wang , Fuli Feng , Yixin Cao , Jizhi Zhang , Tat-Seng Chua
‹ 上一页 1 8 9 10 下一页 ›