Large Language Model

Large language models (LLMs) are sophisticated AI systems designed to process and generate human-like text, aiming to improve various natural language processing tasks. Current research focuses on enhancing LLM safety, efficiency (through techniques like quantization and optimized decoding), and fairness, as well as improving their ability to perform complex reasoning and handle diverse instructions. These advancements are significant because they address critical limitations in current LLMs and pave the way for broader applications across diverse fields, including healthcare, legal tech, and autonomous systems.

Papers

December 18, 2024

Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Models
Jincheol Jung, Hongju Jeong, Eui-Nam Huh
Large Language Model Retrieval Augmented Generation Federated Learning Framework Text Generation Capability Scalable Approach RAG Based
Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
Minkyoung Kim, Yunha Kim, Hyeram Seo, Heejung Choi, Jiye Han, Gaeun Kee, Soyoung Ko, HyoJe Jung, Byeolhee Kim, Young-Hak Kim, Sanghyun Park, Tae Joon Jun
Large Language Model Adversarial Attack Faithful Generation Adversarial Loss Adversarial Suffix
Are LLMs Good Literature Review Writers? Evaluating the Literature Review Writing Ability of Large Language Models
Xuemei Tang, Xufeng Duan, Zhenguang G. Cai
Large Language Model Narrative Review Critique Ability Literature Review Human Written Text English Literature Literature Survey
EvoWiki: Evaluating LLMs on Evolving Knowledge
Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yugang Jiang, Yong Liao
Large Language Model Medical LLM Knowledge Sharing
Context-DPO: Aligning Language Models for Context-Faithfulness
Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu
Large Language Model Language Model ConvQA Face Challenge Contextual Integrity
Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates
Rui Zou, Mengqi Wei, Jintian Feng, Qian Wan, Jianwen Sun, Sannyuya Liu
Large Language Model Value Alignment Multi Agent Debate Agent Interaction Communication Pattern Gradual Pattern
Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs
Imam Nur Bani Yusuf, Lingxiao Jiang
Large Language Model Code Representation Programming Task Code Translation Sequence Transducer Efficient Model Adaptation Property Graph
Lightweight Safety Classification Using Pruned Language Models
Mason Sawtell, Tula Masterman, Sandi Besen, Jim Brown
Large Language Model Transformer Layer Transformer Performance Injection Drug Use Safety Classifier
Large Language Model Enhanced Recommender Systems: Taxonomy, Trend, Application and Future
Qidong Liu, Xiangyu Zhao, Yuhao Wang, Yejing Wang, Zijian Zhang, Yuqi Sun, Xiang Li, Maolin Wang, Pengyue Jia, Chong Chen, Wei Huang, Feng Tian
Large Language Model Language Model Application Proficiency Recommender System Comprehensive Taxonomy Future Reasoning Movie Recommendation Recent Trend Interaction Generation
Safeguarding System Prompts for LLMs
Zhifeng Jiang, Zhihua Jin, Guoliang He
Large Language Model Prompt Programming Prompt Extraction
Generating Diverse Hypotheses for Inductive Reasoning
Kang-il Lee, Hyukhun Koh, Dongryeol Lee, Seunghyun Yoon, Minsung Kim, Kyomin Jung
Large Language Model Reasoning Benchmark Information Redundancy Inductive Reasoning Hypothesis Generation Depth Hypothesis

December 17, 2024

An Automated Explainable Educational Assessment System Built on LLMs
Jiazheng Li, Artem Bobrov, David West, Cesare Aloisi, Yulan He
Large Language Model Better Explainability Robust Evaluation Visual Assessment Educational Assessment
Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation
Samin Mahdizadeh Sani, Pouya Sadeghi, Thuy-Trang Vu, Yadollah Yaghoobzadeh, Gholamreza Haffari
Large Language Model Low Resource Language Adaptation Concern New Language LLaMa LlamaCare Persian Dataset Bilingual Data Cross Lingual Alignment
Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs
Aldo Pareja, Nikhil Shivakumar Nayak, Hao Wang, Krishnateja Killamsetty, Shivchander Sudalairaj, Wenlong Zhao, Seungwook Han, Abhishek Bhandwaldar, Guangxuan Xu, Kai Xu, Ligong Han, Luke Inglis, Akash Srivastava
Large Language Model Model Performance Supervised Fine Tuning Training Dynamic Practical Guide Complete Recipe
Experience of Training a 1.7B-Parameter LLaMa Model From Scratch
Miles Q. Li, Benjamin C. M. Fung, Shih-Chia Huang
Large Language Model Training Data eXperience Report Scratch Project LLaMA Model
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch, Xinpeng Wang, Markus Herklotz, Frauke Kreuter, Barbara Plank, Matthias Assenmacher
Large Language Model Public Sentiment Diverse Opinion Synthetic Generation
SWAN: Preprocessing SGD Enables Adam-Level Performance On LLM Training With Significant Memory Reduction
Chao Ma, Wenbo Gong, Meyer Scetbon, Edward Meeds
Large Language Model Gradient Descent Stochastic Gradient Adam Optimizer LLM Training Memory Reduction
Are Your LLMs Capable of Stable Reasoning?
Junnan Liu, Hongwei Liu, Linchen Xiao, Ziyi Wang, Kuikun Liu, Songyang Gao, Wenwei Zhang, Songyang Zhang, Kai Chen
Large Language Model Complex Reasoning Task Novel Evaluation State of the Art Large Stable Explanation Improved Benchmark
SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation
Yuzheng Cai, Zhenyue Guo, Yiwen Pei, Wanrui Bian, Weiguo Zheng
Large Language Model Knowledge Graph Retrieval Augmented Generation Subgraph Structure Subgraph Pattern
FineGates: LLMs Finetuning with Compression using Stochastic Gates
Jonathan Svirsky, Yehonathan Refael, Ofir Lindenbaum
Large Language Model Low Rank Linear Compression Task Adaptation Learnable Parameter Accuracy Loss Stochastic Gate

Large Language Model

Papers

Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Models

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation

Are LLMs Good Literature Review Writers? Evaluating the Literature Review Writing Ability of Large Language Models

EvoWiki: Evaluating LLMs on Evolving Knowledge

Context-DPO: Aligning Language Models for Context-Faithfulness

Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates

Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs

Lightweight Safety Classification Using Pruned Language Models

Large Language Model Enhanced Recommender Systems: Taxonomy, Trend, Application and Future

Safeguarding System Prompts for LLMs

Generating Diverse Hypotheses for Inductive Reasoning

An Automated Explainable Educational Assessment System Built on LLMs

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation

Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

Experience of Training a 1.7B-Parameter LLaMa Model From Scratch

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study

SWAN: Preprocessing SGD Enables Adam-Level Performance On LLM Training With Significant Memory Reduction

Are Your LLMs Capable of Stable Reasoning?

SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation

FineGates: LLMs Finetuning with Compression using Stochastic Gates