中文
相关论文

相关论文: C-MOP: Integrating Momentum and Boundary-Aware Clu…

200 篇论文

Automated prompt optimization methods (e.g., DSpy, TextGrad) can substantially improve the performance of large language model (LLM), however, their generalization ability across different tasks remains underperformed. In practice, the…

计算与语言 · 计算机科学 2026-05-27 Shuzhi Gong , Hechuan Wen

Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is to use prompts in the form of either discrete tokens or…

计算与语言 · 计算机科学 2022-10-04 Tianyi Tang , Junyi Li , Wayne Xin Zhao , Ji-Rong Wen

Designing optimal prompts and reasoning processes for large language models (LLMs) on domain-specific tasks is both necessary and challenging in real-world applications. Determining how to integrate domain knowledge, enhance reasoning…

人工智能 · 计算机科学 2025-10-27 Yang Zhao , Pu Wang , Hao Frank Yang

In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key…

计算与语言 · 计算机科学 2024-08-13 Huiqiang Jiang , Qianhui Wu , Xufang Luo , Dongsheng Li , Chin-Yew Lin , Yuqing Yang , Lili Qiu

Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via…

计算与语言 · 计算机科学 2025-01-28 Xinyu Tang , Xiaolei Wang , Wayne Xin Zhao , Siyuan Lu , Yaliang Li , Ji-Rong Wen

The rapid advancement of large language models has intensified public concerns about the potential misuse. Therefore, it is important to build trustworthy AI-generated text detection systems. Existing methods neglect stylistic modeling and…

计算与语言 · 计算机科学 2025-09-09 Junxi Wu , Jinpeng Wang , Zheng Liu , Bin Chen , Dongjian Hu , Hao Wu , Shu-Tao Xia

Moderate-sized large language models (LLMs) -- those with 7B or 13B parameters -- exhibit promising machine translation (MT) performance. However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the…

计算与语言 · 计算机科学 2024-06-04 Haoran Xu , Amr Sharaf , Yunmo Chen , Weiting Tan , Lingfeng Shen , Benjamin Van Durme , Kenton Murray , Young Jin Kim

This letter investigates an unmanned aerial vehicle (UAV) network with integrated sensing and communication (ISAC) systems, where multiple UAVs simultaneously sense the locations of ground users and provide communication services with…

信息论 · 计算机科学 2024-11-27 Haoyun Li , Ming Xiao , Kezhi Wang , Dong In Kim , Merouane Debbah

Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when…

计算与语言 · 计算机科学 2026-05-28 Lucas Resck , Isabelle Augenstein , Anna Korhonen

Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be…

计算与语言 · 计算机科学 2026-04-28 Lovisa Hagström , Youna Kim , Haeun Yu , Sang-goo Lee , Richard Johansson , Hyunsoo Cho , Isabelle Augenstein

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) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…

机器学习 · 计算机科学 2026-04-23 Noah Flynn

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

Large Language Models (LLMs) achieve competitive performance across diverse natural language processing (NLP) tasks, yet pretraining is computationally demanding, making optimizer efficiency an important practical consideration. Muon…

机器学习 · 计算机科学 2026-01-22 Jingru Li , Yibo Fan , Huan Li

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among related categories…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Wangyu Wu , Zhenhong Chen , Xiaowen Ma , Wenqiao Zhang , Xianglin Qiu , Siqi Song , Xiaowei Huang , Fei Ma , Jimin Xiao

Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for practical deployment on resource-constrained edge devices. To…

机器学习 · 计算机科学 2025-10-29 Yao Lu , Yuqi Li , Wenbin Xie , Shanqing Yu , Qi Xuan , Zhaowei Zhu , Shiping Wen

The rapid advancement of Large Language Models (LLMs) has inaugurated a transformative epoch in natural language processing, fostering unprecedented proficiency in text generation, comprehension, and contextual scrutiny. Nevertheless,…

机器学习 · 计算机科学 2024-04-22 Cangqing Wang , Yutian Yang , Ruisi Li , Dan Sun , Ruicong Cai , Yuzhu Zhang , Chengqian Fu , Lillian Floyd

Mixture-of-Experts (MoE) architectures have emerged as a promising paradigm for scaling large language models (LLMs) with sparse activation of task-specific experts. Despite their computational efficiency during inference, the massive…

计算与语言 · 计算机科学 2025-04-11 Hongcheng Guo , Juntao Yao , Boyang Wang , Junjia Du , Shaosheng Cao , Donglin Di , Shun Zhang , Zhoujun Li

LLMs have advanced text classification, yet existing paradigms face a trade-off: supervised (label only) fine-tuning is scalable but offers limited reasoning on complex text and lacks broader model transparency, while discrete prompt…

计算与语言 · 计算机科学 2026-05-29 Tianyang Zhou , Wenbo Chen , Pierre Jinghong Liang , Leman Akoglu

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, whose applicability is…

计算与语言 · 计算机科学 2026-03-04 Yexing Du , Youcheng Pan , Zekun Wang , Zheng Chu , Yichong Huang , Kaiyuan Liu , Bo Yang , Yang Xiang , Ming Liu , Bing Qin