paper-with-me

Papers

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications

2024-10-11 · Alexey Zhezherau, Alexei Yanockin

This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By leveraging a dataset combining transcribed real interactions with high-quality synthetic sessions, we aimed to overcome the limitations of scarce, noisy, and domain-specific real data. Synthetic personas and scenarios were employed to enhance training diversity. The study evaluated three models: a base foundational model, a model fine-tuned with real data, and a hybrid fine-tuned model. Experimental results showed that the hybrid model consistently outperformed the others in specific vertical applications, achieving the highest scores across all metrics. Further testing confirmed the hybrid model's superior adaptability and contextual understanding across diverse scenarios. These findings suggest that combining real and synthetic data can significantly improve the robustness and contextual sensitivity of LLMs, particularly in domain-specific and vertical use cases.

📄 PDF Abstract BibTeX arXiv:2410.09168

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Hybrid Latent Reasoning via Reinforcement Learning

2025-05-24 · Zhenrui Yue, Bowen Jin, Huimin Zeng, Honglei Zhuang 외

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent r…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview

2025-03-13 · Norbert Tihanyi, Tamas Bisztray, Mohamed Amine Ferrag, Bilel Cherif 외

Software testing and verification are critical for ensuring the reliability and security of modern software systems. Traditionally, formal verification techniques, such as model checking and theorem proving, have provide…

Automated Theorem Provingsoftware testingVulnerability Detection

LLaRA: Large Language-Recommendation Assistant

2023-12-05 · Jiayi Liao, Sihang Li, Zhengyi Yang, Jiancan Wu 외

Sequential recommendation aims to predict users' next interaction with items based on their past engagement sequence. Recently, the advent of Large Language Models (LLMs) has sparked interest in leveraging them for seque…

Language ModelingLanguage ModellingSequential RecommendationWorld Knowledge

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

2024-10-28 · Hsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao, Wei-Yun Ma 외

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However…

AllData Augmentationtext-classificationText Classification

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

2025-03-06 · Zhijian Zhuo, Yutao Zeng, Ya Wang, Sijun Zhang 외

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, challenges remain in training deep transf…