中文
相关论文

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

200 篇论文

Instruction tuning benefits from large and diverse datasets; however, creating such datasets involves a high cost of human labeling. While synthetic datasets generated by large language models (LLMs) have partly solved this issue, they…

计算与语言 · 计算机科学 2024-08-28 Ritik Sachin Parkar , Jaehyung Kim , Jong Inn Park , Dongyeop Kang

The field of healthcare has increasingly turned its focus towards Large Language Models (LLMs) due to their remarkable performance. However, their performance in actual clinical applications has been underexplored. Traditional evaluations…

Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language…

计算与语言 · 计算机科学 2024-05-09 Yikuan Xia , Jiazun Chen , Xinchi Li , Jun Gao

Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of Large Language Models (LLMs) to various downstream applications. However, the effectiveness of the PEFT diminishes notably when downstream tasks require accurate…

计算与语言 · 计算机科学 2024-05-29 Renzhi Wang , Piji Li

This paper describes a rapid feasibility study of using GPT-4, a large language model (LLM), to (semi)automate data extraction in systematic reviews. Despite the recent surge of interest in LLMs there is still a lack of understanding of how…

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

计算与语言 · 计算机科学 2025-03-21 Ishika Agarwal , Krishnateja Killamsetty , Lucian Popa , Marina Danilevksy

Large Audio Language Models (LALMs) have expanded the interaction with human to speech modality, which introduces great interactive potential, due to the paralinguistic cues implicitly indicating the user context. However, building on the…

声音 · 计算机科学 2026-03-13 Hao Yang , Minghan Wang , Tongtong Wu , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). Currently, many newly introduced PEFT methods are challenging to replicate, deploy, or compare with one another. To address this, we…

计算与语言 · 计算机科学 2026-05-14 Robert Belanec , Ivan Srba , Maria Bielikova

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage…

计算与语言 · 计算机科学 2023-05-01 George Pu , Anirudh Jain , Jihan Yin , Russell Kaplan

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on filtering entire samples, the quality of individual tokens…

计算与语言 · 计算机科学 2026-03-12 Jinlong Pang , Na Di , Zhaowei Zhu , Jiaheng Wei , Hao Cheng , Chen Qian , Yang Liu

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for…

Electronic Patient Record (EPR) systems contain valuable clinical information, but much of it is trapped in unstructured text, limiting its use for research and decision-making. Large language models can extract such information but require…

High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation…

计算与语言 · 计算机科学 2025-01-27 Tomas Horych , Christoph Mandl , Terry Ruas , Andre Greiner-Petter , Bela Gipp , Akiko Aizawa , Timo Spinde

In this paper we present the first investigation into the effectiveness of Large Language Models (LLMs) for Failure Mode Classification (FMC). FMC, the task of automatically labelling an observation with a corresponding failure mode code,…

计算与语言 · 计算机科学 2023-09-18 Michael Stewart , Melinda Hodkiewicz , Sirui Li

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

机器学习 · 计算机科学 2024-11-26 Olivia Ma , Jonathan Passerat-Palmbach , Dmitrii Usynin

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Large language models (LLMs) can label data faster and cheaper than humans for various NLP tasks. Despite their prowess, LLMs may fall short in understanding of complex, sociocultural, or domain-specific context, potentially leading to…

计算与语言 · 计算机科学 2024-02-29 Hannah Kim , Kushan Mitra , Rafael Li Chen , Sajjadur Rahman , Dan Zhang

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across…

计算与语言 · 计算机科学 2024-04-16 Flor Miriam Plaza-del-Arco , Debora Nozza , Dirk Hovy

Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…

计算与语言 · 计算机科学 2024-03-20 Jiuhai Chen , Jonas Mueller

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

计算与语言 · 计算机科学 2024-01-09 Jean Kaddour , Qi Liu