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

September 22, 2024

SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
Hanzhu Chen, Xu Shen, Qitan Lv, Jie Wang, Xiaoqi Ni, Jieping Ye
Large Language Model Knowledge Graph Knowledge Intensive Task Specific Knowledge Graph Automatic Construction
Investigating Layer Importance in Large Language Models
Yang Zhang, Yanfei Dong, Kenji Kawaguchi
Large Language Model Multi Layer Feature Attribution
LLMs are One-Shot URL Classifiers and Explainers
Fariza Rashid, Nishavi Ranaweera, Ben Doyle, Suranga Seneviratne
Large Language Model Url Detection URL Classification

September 21, 2024

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
Xinghua Zhang, Haiyang Yu, Yongbin Li, Minzheng Wang, Longze Chen, Fei Huang
Large Language Model Barzilai Borwein Technique Recent Trend Conversational Data Future Command
Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks
Liujianfu Wang, Yuyang Du, Jingqi Lin, Kexin Chen, Soung Chang Liew
Large Language Model Fine Tuning Timely Communication Deep Understanding Language Model Fine Tuning Computer Network
QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling
Blessed Guda, Gabrial Zencha A., Lawrence Francis, Carlee Joe-Wong
Large Language Model Retrieval Augmented Generation Question Answering Yes No Question Smaller Language Model Continuous Option Complementary Metal Oxide Semiconductor Telecom Domain
Routing in Sparsely-gated Language Models responds to Context
Stefan Arnold, Marian Fietta, Dilara Yesilbas
Large Language Model Language Model Context Information Mixture of Expert Routing Problem Context Dependent Token Expert Combination
Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction
Amrit Diggavi Seshadri
Large Language Model Pre Trained Transformer Transformer Based Large Language Model Hidden Representation Shortcut Feature Independent Jump
PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL
Ruilin Luo, Liyuan Wang, Binghuai Lin, Zicheng Lin, Yujiu Yang
Large Language Model Text to SQL Inductive Reasoning Din SQL Categorical Structure
OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching
Zhangcheng Qiang, Kerry Taylor, Weiqing Wang, Jing Jiang
Large Language Model Benchmark Dataset Language Model Hallucination LLM Hallucination Ontology Alignment Ontology Matching
Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
Prasoon Bajpai, Niladri Chatterjee, Subhabrata Dutta, Tanmoy Chakraborty
Large Language Model Open Source Large Language Model OpenAI GPT Scientific Communication
StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models
Nikolai Rozanov, Marek Rei
Large Language Model Context Learning Complex Reasoning Task Planning Internal State Artificial Intelligence Method State Observation
LLM Agents as 6G Orchestrator: A Paradigm for Task-Oriented Physical-Layer Automation
Zhuoran Xiao, Chenhui Ye, Yunbo Hu, Honggang Yuan, Yihang Huang, Yijia Feng, Liyu Cai, Jiang Chang
Large Language Model Chatbot Response Agent System Task Specification Hui Walter Paradigm Physical Layer Co Orchestration Artificial Intelligence Native Reactive Programming
Bias and Toxicity in Role-Play Reasoning
Jinman Zhao, Zifan Qian, Linbo Cao, Yining Wang, Yitian Ding
Large Language Model Language Model Absolute Stance Bias Non Toxic Role Play NLP Benchmark

September 20, 2024

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang
Large Language Model Text Generation Task Soft Prompt Memorization Effect LLM Explanation
Measuring Copyright Risks of Large Language Model via Partial Information Probing
Weijie Zhao, Huajie Shao, Zhaozhuo Xu, Suzhen Duan, Denghui Zhang
Large Language Model Training Data Linear Probing Iterative Prompting
The Impact of Large Language Models in Academia: from Writing to Speaking
Mingmeng Geng, Caixi Chen, Yanru Wu, Dongping Chen, Yao Wan, Pan Zhou
Large Language Model Global Impact Speech Analysis Implicit Bias LLM Generated Speech Interaction
OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
Stephen Zhang, Vardan Papyan
Large Language Model Vision Transformer Text Summarization Many Sparse Model Compression Low Rank Decomposition Input Embeddings
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto, Luca Cagliero, Paolo Garza
Large Language Model Language Generation Cross Entropy Loss Segmentation Loss
ChainBuddy: An AI Agent System for Generating LLM Pipelines
Jingyue Zhang, Ian Arawjo
Large Language Model Side Chain Agent System Open Ended AI Assistance LLM Based Pipeline Evaluation Funnel

Large Language Model

Papers

SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs

Investigating Layer Importance in Large Language Models

LLMs are One-Shot URL Classifiers and Explainers

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends

Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks

QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling

Routing in Sparsely-gated Language Models responds to Context

Normalized Narrow Jump To Conclusions: Normalized Narrow Shortcuts for Parameter Efficient Early Exit Transformer Prediction

PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL

OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching

Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators

StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models

LLM Agents as 6G Orchestrator: A Paradigm for Task-Oriented Physical-Layer Automation

Bias and Toxicity in Role-Play Reasoning

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting

Measuring Copyright Risks of Large Language Model via Partial Information Probing

The Impact of Large Language Models in Academia: from Writing to Speaking

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition

Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning

ChainBuddy: An AI Agent System for Generating LLM Pipelines