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

January 13, 2025

SafePowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models
Fabien Bernier, Jun Cao, Maxime Cordy, Salah Ghamizi
Large Language Model Graph Neural Network Optimization Purpose Power Grid Graph Embeddings Optimal Power Flow Power Network
TiEBe: A Benchmark for Assessing the Current Knowledge of Large Language Models
Thales Sales Almeida, Giovana Kerche Bonás, João Guilherme Alves Santos, Hugo Abonizio, Rodrigo Nogueira
Large Language Model New Benchmark Full Model Continual LEArning Data Centric Large Language Research Trend
Emergent effects of scaling on the functional hierarchies within large language models
Paul C. Bogdan
Large Language Model Language Model Attention Mechanism Part Whole Hierarchy Deep Layer Level Semantics Early Layer
LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks
Zan-Kai Chong, Hiroyuki Ohsaki, Bryan Ng
Large Language Model Network Programming Blockchain Based Platform State of the Art Large Incremental Knowledge
Lifelong Learning of Large Language Model based Agents: A Roadmap
Junhao Zheng, Chengming Shi, Xidi Cai, Qiuke Li, Duzhen Zhang, Chenxing Li, Dong Yu, Qianli Ma
Large Language Model Incremental Learning Agent Smith LLM Based Agent Lifelong Learning Requirement Based Roadmap Continuous Adaptation Lifelong Learning System
Breaking Memory Limits: Gradient Wavelet Transform Enhances LLMs Training
Ziqing Wen, Ping Luo, Jiahuan Wang, Xiaoge Deng, Jinping Zou, Kun Yuan, Tao Sun, Dongsheng Li
Large Language Model Training Data Efficient Training Memory Efficient Wavelet Transform
Touched by ChatGPT: Using an LLM to Drive Affective Tactile Interaction
Qiaoqiao Ren, Tony Belpaeme
Large Language Model ChatGPT Generated Conversation Tactile Robotic System Tactile Signal Haptic Information Tactile Estimation Tactile Interaction
ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training
Jiayang Wu, Wensheng Gan, Jiahao Zhang, Philip S. Yu
Large Language Model Knowledge Graph Anomaly Detection Representation Learning Unstructured Data Multi Channel
Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities
ZeKe Xiao, Qin Wang, Hammond Pearce, Shiping Chen
Large Language Model Security Vulnerability Smart Contract Logic Reasoning LangId Magic Spell

January 12, 2025

Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives
Xinyao Ma, Rui Zhu, Zihao Wang, Jingwei Xiong, Qingyu Chen, Haixu Tang, L. Jean Camp, Lucila Ohno-Machado
Large Language Model Clinical Narrative Patient Centric LLM Simulation Procedural Persona
A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context
Noureldin Zahran, Aya E. Fouda, Radwa J. Hanafy, Mohammed E. Fouda
Large Language Model Multilingual Model Mental Health Comprehensive Evaluation Arabic Dialect Arabic Language
An efficient approach to represent enterprise web application structure using Large Language Model in the service of Intelligent Quality Engineering
Zaber Al Hassan Ayon, Gulam Husain, Roshankumar Bisoi, Waliur Rahman, Dr Tom Osborn
Large Language Model Generative AI Service Provider Modular Framework Efficient Approach
Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification
Shijing Chen, Mohamed Reda Bouadjenek, Shoaib Jameel, Usman Naseem, Basem Suleiman, Flora D. Salim, Hakim Hacid, Imran Razzak
Large Language Model Classification Code Comprehensive Taxonomy Hierarchical Classification Hierarchical Structure LLM Based Framework
Event Argument Extraction with Enriched Prompts
Chen Liang
Large Language Model Language Model Event Argument Extraction Argument Role
Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences
Liu Yu, Ludie Guo, Ping Kuang, Fan Zhou
Large Language Model Full Model Pre Trained Language Model Gender Bias Debiasing Framework Fairness Assessment Non Pun Sentence
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
Ji Soo Lee, Jongha Kim, Jeehye Na, Jinyoung Park, Hyunwoo J. Kim
Large Language Model Fine Grained Optimization Purpose Video Captioning Dense Video Captioning Preference Based
Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation
Shunfan Zheng, Xiechi Zhang, Gerard de Melo, Xiaoling Wang, Linlin Wang
Large Language Model Fine Grained Multiple Choice Divide and Conquer
ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian
Mykyta Syromiatnikov, Victoria Ruvinskaya, Anastasiya Troynina
Large Language Model Language Model Reasoning Capability Comprehensive Benchmark Russian Language G Eval

January 11, 2025

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models
Veronika Smilga
Large Language Model Language Model Training Data Language Model Generation Biased Association Semantic Leakage
Quantifying Relational Exploration in Cultural Heritage Knowledge Graphs with LLMs: A Neuro-Symbolic Approach
Mohammed Maree
Large Language Model Wikidata Statement Neuro Symbolic Approach Relation Pattern LLM Explanation Relation Discovery

Large Language Model

Papers

SafePowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models

TiEBe: A Benchmark for Assessing the Current Knowledge of Large Language Models

Emergent effects of scaling on the functional hierarchies within large language models

LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks

Lifelong Learning of Large Language Model based Agents: A Roadmap

Breaking Memory Limits: Gradient Wavelet Transform Enhances LLMs Training

Touched by ChatGPT: Using an LLM to Drive Affective Tactile Interaction

ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training

Logic Meets Magic: LLMs Cracking Smart Contract Vulnerabilities

Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives

A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context

An efficient approach to represent enterprise web application structure using Large Language Model in the service of Intelligent Quality Engineering

Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification

Event Argument Extraction with Enriched Prompts

Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation

ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models

Quantifying Relational Exploration in Cultural Heritage Knowledge Graphs with LLMs: A Neuro-Symbolic Approach