中文
相关论文

相关论文: Selective Fine-tuning on LLM-labeled Data May Redu…

200 篇论文

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based…

计算与语言 · 计算机科学 2023-06-07 Josh Magnus Ludan , Yixuan Meng , Tai Nguyen , Saurabh Shah , Qing Lyu , Marianna Apidianaki , Chris Callison-Burch

Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abnormality classification, and clinical decision-making. Among…

We introduce a large language model (LLM) capable of processing speech inputs and show that tuning it further with reinforcement learning on human preference (RLHF) enables it to adapt better to disordered speech than traditional…

音频与语音处理 · 电气工程与系统科学 2025-01-03 Chirag Nagpal , Subhashini Venugopalan , Jimmy Tobin , Marilyn Ladewig , Katherine Heller , Katrin Tomanek

Large Language Models (LLMs) have proven highly effective in automating software engineering tasks, bridging natural language and code semantics to achieve notable results in code generation and summarization. However, their scale incurs…

软件工程 · 计算机科学 2026-01-22 Md Zahidul Haque , Saima Afrin , Antonio Mastropaolo

Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…

计算与语言 · 计算机科学 2024-08-13 Chenyang Zhao , Xueying Jia , Vijay Viswanathan , Tongshuang Wu , Graham Neubig

Graph neural networks (GNNs) have become the preferred models for node classification in graph data due to their robust capabilities in integrating graph structures and attributes. However, these models heavily depend on a substantial…

机器学习 · 计算机科学 2025-05-19 Taiyan Zhang , Renchi Yang , Yurui Lai , Mingyu Yan , Xiaochun Ye , Dongrui Fan

Personality detection automatically identifies an individual's personality from various data sources, such as social media texts. However, as the parameter scale of language models continues to grow, the computational cost becomes…

计算与语言 · 计算机科学 2025-04-09 Lingzhi Shen , Yunfei Long , Xiaohao Cai , Guanming Chen , Imran Razzak , Shoaib Jameel

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

计算与语言 · 计算机科学 2025-06-27 Zhengyan Shi

Programmatic weak supervision (PWS) significantly reduces human effort for labeling data by combining the outputs of user-provided labeling functions (LFs) on unlabeled datapoints. However, the quality of the generated labels depends…

机器学习 · 计算机科学 2025-06-05 Chenjie Li , Amir Gilad , Boris Glavic , Zhengjie Miao , Sudeepa Roy

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

机器学习 · 计算机科学 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…

计算与语言 · 计算机科学 2024-10-23 Benedict Aaron Tjandra , Muhammed Razzak , Jannik Kossen , Kunal Handa , Yarin Gal

Textual data annotation, the process of labeling or tagging text with relevant information, is typically costly, time-consuming, and labor-intensive. While large language models (LLMs) have demonstrated their potential as direct…

计算与语言 · 计算机科学 2025-08-12 Yu-Min Tseng , Wei-Lin Chen , Chung-Chi Chen , Hsin-Hsi Chen

Large language models (LLMs) have shown promise for event log analysis, but their high computational requirements, reliance on cloud infrastructure, and security concerns limit practical deployment. In addition, most existing approaches…

密码学与安全 · 计算机科学 2026-05-08 Siraaj Akhtar , Saad Khan , Simon Parkinson

Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant…

计算与语言 · 计算机科学 2024-12-06 Yu Yang , Siddhartha Mishra , Jeffrey N Chiang , Baharan Mirzasoleiman

Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have…

计算与语言 · 计算机科学 2024-01-26 Madhumita Sushil , Travis Zack , Divneet Mandair , Zhiwei Zheng , Ahmed Wali , Yan-Ning Yu , Yuwei Quan , Atul J. Butte

This paper explores the use of large language models (LLMs) for annotating document utility in training retrieval and retrieval-augmented generation (RAG) systems, aiming to reduce dependence on costly human annotations. We address the gap…

信息检索 · 计算机科学 2025-10-10 Hengran Zhang , Minghao Tang , Keping Bi , Jiafeng Guo , Shihao Liu , Daiting Shi , Dawei Yin , Xueqi Cheng

Search methods based on Pretrained Language Models (PLM) have demonstrated great effectiveness gains compared to statistical and early neural ranking models. However, fine-tuning PLM-based rankers requires a great amount of annotated…

信息检索 · 计算机科学 2023-09-13 Sophia Althammer , Guido Zuccon , Sebastian Hofstätter , Suzan Verberne , Allan Hanbury

Lately, instruction-based techniques have made significant strides in improving performance in few-shot learning scenarios. They achieve this by bridging the gap between pre-trained language models and fine-tuning for specific downstream…

信息检索 · 计算机科学 2024-01-25 Hiranmai Sri Adibhatla , Pavan Baswani , Manish Shrivastava

Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging as they usually…

计算与语言 · 计算机科学 2024-06-10 Xiongtao Zhou , Jie He , Yuhua Ke , Guangyao Zhu , Víctor Gutiérrez-Basulto , Jeff Z. Pan

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

计算与语言 · 计算机科学 2025-10-03 Dimitar Peshevski , Kiril Blazhevski , Martin Popovski , Gjorgji Madjarov
‹ 上一页 1 8 9 10 下一页 ›