中文
相关论文

相关论文: Learning Non-linguistic Skills without Sacrificing…

200 篇论文

Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks. Though linguistically proficient, the inability of these models…

计算与语言 · 计算机科学 2022-11-07 Mandar Sharma , Nikhil Muralidhar , Naren Ramakrishnan

Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP), particularly in Natural Language Understanding (NLU) tasks. As we progress toward an agentic world where LLM-based agents autonomously handle…

计算与语言 · 计算机科学 2025-04-03 Naimul Haque

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical computations. However, even for the simplest…

计算与语言 · 计算机科学 2024-09-04 Wei Zhang , Chaoqun Wan , Yonggang Zhang , Yiu-ming Cheung , Xinmei Tian , Xu Shen , Jieping Ye

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common…

计算与语言 · 计算机科学 2024-01-09 Chen-An Li , Hung-Yi Lee

Large Language Models (LLMs) have shown remarkable performance in various natural language processing tasks but face challenges in mathematical reasoning, where complex problem-solving requires both linguistic understanding and mathematical…

计算与语言 · 计算机科学 2025-03-20 Shuguang Chen , Guang Lin

Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English…

计算与语言 · 计算机科学 2024-05-28 Zixian Huang , Wenhao Zhu , Gong Cheng , Lei Li , Fei Yuan

When finetuning large language models for specialized tasks such as mathematical reasoning, models exhibit catastrophic forgetting, losing previously learned capabilities. We investigate this by finetuning Flan-T5-Base (250M parameters) on…

机器学习 · 计算机科学 2025-12-17 John Graham Reynolds

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

计算与语言 · 计算机科学 2024-10-23 Chonghua Liao , Ruobing Xie , Xingwu Sun , Haowen Sun , Zhanhui Kang

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…

计算与语言 · 计算机科学 2025-05-26 Chi-Yuan Hsiao , Ke-Han Lu , Kai-Wei Chang , Chih-Kai Yang , Wei-Chih Chen , Hung-yi Lee

Prompting techniques have significantly enhanced the capabilities of Large Language Models (LLMs) across various complex tasks, including reasoning, planning, and solving math word problems. However, most research has predominantly focused…

计算与语言 · 计算机科学 2024-05-24 Neisarg Dave , Daniel Kifer , C. Lee Giles , Ankur Mali

Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better…

计算与语言 · 计算机科学 2025-04-01 Yongce Li , Chung-En Sun , Tsui-Wei Weng

Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks. As large language…

计算与语言 · 计算机科学 2025-01-07 Yun Luo , Zhen Yang , Fandong Meng , Yafu Li , Jie Zhou , Yue Zhang

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

机器学习 · 计算机科学 2026-01-27 Olaf Yunus Laitinen Imanov

The association between language and (non-linguistic) thinking ability in humans has long been debated, and recently, neuroscientific evidence of brain activity patterns has been considered. Such a scientific context naturally raises an…

计算与语言 · 计算机科学 2025-02-18 Riku Kisako , Tatsuki Kuribayashi , Ryohei Sasano

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

Recent work has shown that large pretrained Language Models (LMs) can not only perform remarkably well on a range of Natural Language Processing (NLP) tasks but also start improving on reasoning tasks such as arithmetic induction, symbolic…

计算与语言 · 计算机科学 2022-08-11 Jing Qian , Hong Wang , Zekun Li , Shiyang Li , Xifeng Yan

Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities. In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream…

计算与语言 · 计算机科学 2024-08-09 Junhao Zheng , Shengjie Qiu , Qianli Ma

Large pre-trained language models (LMs) are known to encode substantial amounts of linguistic information. However, high-level reasoning skills, such as numerical reasoning, are difficult to learn from a language-modeling objective only.…

计算与语言 · 计算机科学 2020-04-10 Mor Geva , Ankit Gupta , Jonathan Berant

Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) undergoing continual…

计算与语言 · 计算机科学 2025-09-03 Ege Süalp , Mina Rezaei

LLMs have made significant progress in the field of mathematical reasoning, but whether they have true the mathematical understanding ability is still controversial. To explore this issue, we propose a new perturbation framework to evaluate…

人工智能 · 计算机科学 2025-11-12 Zhishen Sun , Guang Dai , Ivor Tsang , Haishan Ye
‹ 上一页 1 2 3 10 下一页 ›