中文
相关论文

相关论文: Fine-Tuning or Fine-Failing? Debunking Performance…

200 篇论文

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…

计算与语言 · 计算机科学 2024-02-06 Liang Zhang , Katherine Jijo , Spurthi Setty , Eden Chung , Fatima Javid , Natan Vidra , Tommy Clifford

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

计算与语言 · 计算机科学 2024-03-15 Haoran Yang , Yumeng Zhang , Jiaqi Xu , Hongyuan Lu , Pheng Ann Heng , Wai Lam

This paper investigates the impact of domain-specific model fine-tuning and of reasoning mechanisms on the performance of question-answering (Q&A) systems powered by large language models (LLMs) and Retrieval-Augmented Generation (RAG).…

Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently…

人工智能 · 计算机科学 2024-01-31 Oded Ovadia , Menachem Brief , Moshik Mishaeli , Oren Elisha

We study the limitations of Large Language Models (LLMs) for the task of response generation in human-machine dialogue. Several techniques have been proposed in the literature for different dialogue types (e.g., Open-Domain). However, the…

计算与语言 · 计算机科学 2024-08-06 Simone Alghisi , Massimo Rizzoli , Gabriel Roccabruna , Seyed Mahed Mousavi , Giuseppe Riccardi

There are two common ways in which developers are incorporating proprietary and domain-specific data when building applications of Large Language Models (LLMs): Retrieval-Augmented Generation (RAG) and Fine-Tuning. RAG augments the prompt…

Fine-tuning large language models (LLMs) for machine translation has shown improvements in overall translation quality. However, it is unclear what is the impact of fine-tuning on desirable LLM behaviors that are not present in neural…

计算与语言 · 计算机科学 2024-08-07 David Stap , Eva Hasler , Bill Byrne , Christof Monz , Ke Tran

Despite their success in many natural language tasks, solving math problems remains a significant challenge for large language models (LLMs). A large gap exists between LLMs' pass-at-one and pass-at-N performance in solving math problems,…

计算与语言 · 计算机科学 2023-10-17 Yixin Liu , Avi Singh , C. Daniel Freeman , John D. Co-Reyes , Peter J. Liu

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

计算与语言 · 计算机科学 2025-03-06 Boris Nazarov , Darya Frolova , Yackov Lubarsky , Alexei Gaissinski , Pavel Kisilev

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to improve factuality in large language models (LLMs) by grounding their outputs in retrieved documents. However, ensuring perfect retrieval of relevant information…

计算与语言 · 计算机科学 2025-12-04 Zhan Peng Lee , Andre Lin , Calvin Tan

This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering,…

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

计算与语言 · 计算机科学 2025-10-28 Amit Agarwal , Hansa Meghwani , Hitesh Laxmichand Patel , Tao Sheng , Sujith Ravi , Dan Roth

There is a compelling necessity from enterprises for fine tuning LLMs (Large Language Models) o get them trained on proprietary domain knowledge. The challenge is to imbibe the LLMs with domain specific knowledge using the most optimial…

软件工程 · 计算机科学 2024-04-18 Mathav Raj J , Kushala VM , Harikrishna Warrier , Yogesh Gupta

Unit testing plays a pivotal role in software development, improving software quality and reliability. However, generating effective test cases manually is time-consuming, prompting interest in unit testing research. Recently, Large…

软件工程 · 计算机科学 2024-12-24 Ye Shang , Quanjun Zhang , Chunrong Fang , Siqi Gu , Jianyi Zhou , Zhenyu Chen

Large Language Models (LLMs) have been widely applied in various professional fields. By fine-tuning the models using domain specific question and answer datasets, the professional domain knowledge and Q\&A abilities of these models have…

计算与语言 · 计算机科学 2024-07-17 Qimin Yang , Rongsheng Wang , Jiexin Chen , Runqi Su , Tao Tan

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

机器学习 · 计算机科学 2024-11-07 Quinn Leng , Jacob Portes , Sam Havens , Matei Zaharia , Michael Carbin

In the evolving landscape of conversational AI, generating concise, context-aware, and human-like dialogue using small and medium-sized language models (LLMs) remains a complex challenge. This study investigates the influence of LoRA rank,…

计算与语言 · 计算机科学 2025-04-15 Chitranshu Harbola , Anupam Purwar

The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing…

信息检索 · 计算机科学 2024-08-02 Spurthi Setty , Harsh Thakkar , Alyssa Lee , Eden Chung , Natan Vidra

Systematic reviews traditionally have taken considerable amounts of human time and energy to complete, in part due to the extensive number of titles and abstracts that must be reviewed for potential inclusion. Recently, researchers have…

计算与语言 · 计算机科学 2026-03-27 Kweku Yamoah , Noah Schroeder , Emmanuel Dorley , Neha Rani , Caleb Schutz

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

人工智能 · 计算机科学 2025-08-08 Chang Tian , Matthew B. Blaschko , Mingzhe Xing , Xiuxing Li , Yinliang Yue , Marie-Francine Moens
‹ 上一页 1 2 3 10 下一页 ›