Fine Tuned LLM

Fine-tuning large language models (LLMs) adapts pre-trained models to specific tasks by training them on targeted datasets, improving performance and efficiency for various applications. Current research emphasizes cost-effective fine-tuning strategies, including techniques like reinforcement learning from human feedback and parameter-efficient fine-tuning methods (e.g., LoRA, adapters), as well as exploring optimal data representation and generation for improved model generalization and accuracy across diverse domains (e.g., code generation, entity matching, text classification). This work is significant because it enables the deployment of powerful LLMs in resource-constrained environments and enhances their applicability to specialized tasks, impacting fields ranging from healthcare and finance to software engineering and cybersecurity.

Papers

October 11, 2024

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
Yanfeng Jiang, Zelan Yang, Bohua Chen, Shen Li, Yong Li, Tao Li
Large Language Model Structured Dropout Fine Tuned LLM Group Wise Delta Compression

October 3, 2024

Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications
Oren Sultan, Alex Khasin, Guy Shiran, Asnat Greenstein-Messica, Dafna Shahaf
Fine Tuning Real Time Fine Tuned LLM Tool Augmented LLM

September 27, 2024

VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback
Guoxi Zhang, Jiuding Duan
Reinforcement Learning Human Feedback Fine Tuned LLM Preference Datasets Dataset Creation Expert Feedback Preference Dataset

September 19, 2024

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
Mingjie Liu, Yun-Da Tsai, Wenfei Zhou, Haoxing Ren
Code Generation Synthetic Data Generation Contextual Representation Fine Tuned LLM Hardware Description Language Adaptive Machine

September 12, 2024

Fine-tuning Large Language Models for Entity Matching
Aaron Steiner, Ralph Peeters, Christian Bizer
Pre Trained Language Model Generative Large Language Model Entity Matching Fine Tuned LLM LLM Explanation

August 6, 2024

Topic Modeling with Fine-tuning LLMs and Bag of Sentences
Johannes Schneider
Large Language Model Topic Modeling Topic Model Bag Prototype Fine Tuned LLM Topic Distribution Non Pun Sentence

July 22, 2024

Improving Minimum Bayes Risk Decoding with Multi-Prompt
David Heineman, Yao Dou, Wei Xu
Generation Task Fine Tuned LLM Minimum Bayes Risk One Line Prompt

July 19, 2024

Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation
Joy Mahapatra, Utpal Garain
Global Impact State of the Art Data to Text Generation Model Size State of the Art LLM Fine Tuned LLM Small LLM

June 27, 2024

Decoding-Time Language Model Alignment with Multiple Objectives
Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon S. Du
Language Model Multi Objective Multiple Objective Alignment Approach Language Model Alignment Fine Tuned LLM Preference Based

June 12, 2024

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification
Martin Juan José Bucher, Marco Martini
Medical LLM Generative AI Text Classification BERT Model Generative AI Model Fine Tuned LLM

June 9, 2024

Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models
Shraboni Sarker, Ahmad Tamim Hamad, Hulayyil Alshammari, Viviana Grieco, Praveen Rao
Large Language Model Content Analysis Fine Tuned LLM Spanish Language Model

May 21, 2024

Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction
Guangyao Lu, Yulin Liu
Strong Generalization Fine Tuning High Explainability Fact Checking Mining Complex Fact Verification Fine Tuned LLM Self Directed Learning

April 18, 2024

OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data
Chandeepa Dissanayake, Lahiru Lowe, Sachith Gunasekara, Yasiru Ratnayake
Fine Tuning Instruction Data Instruction Fine Tuning Cost Effective Fine Tuned LLM Synthetic Instruction Open Model

April 2, 2024

Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation
Veronica Valeros, Anna Širokova, Carlos Catania, Sebastian Garcia
Machine Translation Integral Role View Translation Deep Understanding Fine Tuned Large Language Model Fine Tuned LLM Translation Accuracy

April 1, 2024

LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction
Bo Zou, Chao Yang, Yu Qiao, Chengbin Quan, Youjian Zhao
Feature Interaction Visual Instruction Tuning Fine Tuned LLM Purple LLaMA CyberSecEval Modal Fine Tuning

March 23, 2024

Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations
Mathav Raj J, Kushala VM, Harikrishna Warrier, Yogesh Gupta
Retrieval Augmented Generation Movie Recommendation LLM Fine Tuning Practical Guide Open Source LLM Company Name Fine Tuned LLM

March 5, 2024

Towards Training A Chinese Large Language Model for Anesthesiology
Zhonghai Wang, Jie Jiang, Yibing Zhan, Bohao Zhou, Yanhong Li, Chong Zhang, Liang Ding, Hua Jin, Jun Peng, Xu Lin, Weifeng Liu
Training Data Medical LLM Foundation Model Medical Data Fine Tuned LLM Medical Large Language Model Chinese Large Language Model

February 22, 2024

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Yixuan Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao
Language Model Fine Tuning Backdoor Attack Jailbreak Attack Safety Alignment Fine Tuned LLM

February 19, 2024

Uncertainty quantification in fine-tuned LLMs using LoRA ensembles
Oleksandr Balabanov, Hampus Linander
Large Language Model Uncertainty Quantification Low Rank Adaptation Fine Tuned Model Fine Tuned LLM Fast LoRA

February 12, 2024

Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
Z Liu, J Lou, W Bao, Y Hu, B Li, Z Qin, K Ren
Large Language Model Fine Tuning Autoregressive Language Model Zeroth Order Private Algorithm Differential Privacy SGD Fine Tuned LLM

Fine Tuned LLM

Papers

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization

Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications

VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

Fine-tuning Large Language Models for Entity Matching

Topic Modeling with Fine-tuning LLMs and Bag of Sentences

Improving Minimum Bayes Risk Decoding with Multi-Prompt

Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation

Decoding-Time Language Model Alignment with Multiple Objectives

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Seventeenth-Century Spanish American Notary Records for Fine-Tuning Spanish Large Language Models

Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction

OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data

Towards Better Understanding of Cybercrime: The Role of Fine-Tuned LLMs in Translation

LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction

Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations

Towards Training A Chinese Large Language Model for Anesthesiology

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

Uncertainty quantification in fine-tuned LLMs using LoRA ensembles

Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning