中文
相关论文

相关论文: Llama SLayer 8B: Shallow Layers Hold the Key to Kn…

200 篇论文

Through additional training, we explore embedding specialized scientific knowledge into the Llama 2 Large Language Model (LLM). Key findings reveal that effective knowledge integration requires reading texts from multiple perspectives,…

计算与语言 · 计算机科学 2023-12-19 Kan Hatakeyama-Sato , Yasuhiko Igarashi , Shun Katakami , Yuta Nabae , Teruaki Hayakawa

Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, their general-purpose nature often limits their effectiveness…

计算与语言 · 计算机科学 2025-09-03 Zirui Song , Bin Yan , Yuhan Liu , Miao Fang , Mingzhe Li , Rui Yan , Xiuying Chen

Although large language models (LLMs) excel in knowledge recall and reasoning, their static nature leads to outdated information as the real world evolves or when adapting to domain-specific knowledge, highlighting the need for effective…

计算与语言 · 计算机科学 2025-04-02 Ruoxi Xu , Yunjie Ji , Boxi Cao , Yaojie Lu , Hongyu Lin , Xianpei Han , Ben He , Yingfei Sun , Xiangang Li , Le Sun

Leading open-source large language models (LLMs) such as Llama-3.1-Instruct-405B are extremely capable at generating text, answering questions, and solving a variety of natural language understanding tasks. However, they incur higher…

机器学习 · 计算机科学 2024-10-25 Anup Shirgaonkar , Nikhil Pandey , Nazmiye Ceren Abay , Tolga Aktas , Vijay Aski

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

计算与语言 · 计算机科学 2025-01-08 Yuchun Fan , Yongyu Mu , Yilin Wang , Lei Huang , Junhao Ruan , Bei Li , Tong Xiao , Shujian Huang , Xiaocheng Feng , Jingbo Zhu

The advent of Large Language Models (LLM) has revolutionized the field of natural language processing, enabling significant progress in various applications. One key area of interest is the construction of Knowledge Bases (KB) using these…

计算与语言 · 计算机科学 2023-08-28 Anmol Nayak , Hari Prasad Timmapathini

Large language models (LLMs) have attracted significant attention due to their impressive general capabilities across diverse downstream tasks. However, without domain-specific optimization, they often underperform on specialized knowledge…

计算与语言 · 计算机科学 2025-09-25 Kangtao Lv , Haibin Chen , Yujin Yuan , Langming Liu , Shilei Liu , Yongwei Wang , Wenbo Su , Bo Zheng

As the knowledge of large language models (LLMs) becomes outdated over time, there is a growing need for efficient methods to update them, especially when injecting proprietary information. Our study reveals that comprehension-intensive…

计算与语言 · 计算机科学 2025-05-26 Essa Jan , Moiz Ali , Muhammad Saram Hassan , Fareed Zaffar , Yasir Zaki

With the growing demand for deploying large language models (LLMs) across diverse applications, improving their inference efficiency is crucial for sustainable and democratized access. However, retraining LLMs to meet new user-specific…

机器学习 · 计算机科学 2026-01-21 Mingyu Yang , Mehdi Rezagholizadeh , Guihong Li , Vikram Appia , Emad Barsoum

Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM…

计算与语言 · 计算机科学 2025-08-11 Hugo Abonizio , Thales Almeida , Roberto Lotufo , Rodrigo Nogueira

Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously acquired reasoning abilities. This tension reflects a…

人工智能 · 计算机科学 2026-05-26 Mustafa Hayri Bilgin , Mariam Barry , Albert Bifet , Azzedine Idir Ait Said , Soumya Banerjee

Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying…

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

机器学习 · 计算机科学 2026-05-20 Fei Liu , Rui Zhang , Xi Lin , Zhichao Lu , Qingfu Zhang

While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge…

机器学习 · 计算机科学 2026-03-24 Kexian Tang , Jiani Wang , Shaowen Wang , Kaifeng Lyu

The performance of Large Language Models (LLMs) on many tasks is greatly limited by the knowledge learned during pre-training and stored in the model's parameters. Low-rank adaptation (LoRA) is a popular and efficient training technique for…

Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow…

人工智能 · 计算机科学 2026-01-28 Xinyuan Song , Keyu Wang , PengXiang Li , Lu Yin , Shiwei Liu

Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters. To enhance this implicit knowledge, we propose Knowledge Injection into Language Models (KILM), a novel approach that injects…

计算与语言 · 计算机科学 2023-02-21 Yan Xu , Mahdi Namazifar , Devamanyu Hazarika , Aishwarya Padmakumar , Yang Liu , Dilek Hakkani-Tür

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

机器学习 · 计算机科学 2024-12-30 Rui Pan , Xiang Liu , Shizhe Diao , Renjie Pi , Jipeng Zhang , Chi Han , Tong Zhang

The recent surge in Multimodal Large Language Models (MLLMs) has showcased their remarkable potential for achieving generalized intelligence by integrating visual understanding into Large Language Models.Nevertheless, the sheer model size…

计算与语言 · 计算机科学 2024-07-30 Shilin Xu , Xiangtai Li , Haobo Yuan , Lu Qi , Yunhai Tong , Ming-Hsuan Yang
‹ 上一页 1 2 3 10 下一页 ›