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

October 19, 2024

AutoFPDesigner: Automated Flight Procedure Design Based on Multi-Agent Large Language Model
Longtao Zhu, Hongyu Yang, Ge Song, Xin Ma, Yanxin Zhang, Yulong Ji
Large Language Model Multi Agent Collaboration Automated Design Navigation Performance
LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model
Tianqianjin Lin, Pengwei Yan, Kaisong Song, Zhuoren Jiang, Yangyang Kang, Jun Lin, Weikang Yuan, Junjie Cao, Changlong Sun, Xiaozhong Liu
Large Language Model Full Model Graph Augmentation Graph Learning Task Graph Foundation Model Effective Graph

October 18, 2024

SPRIG: Improving Large Language Model Performance by System Prompt Optimization
Lechen Zhang, Tolga Ergen, Lajanugen Logeswaran, Moontae Lee, David Jurgens
Large Language Model Optimization Purpose Complex Prompt Style PROMPT Prompt Programming Single Population Optimization Task
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen
Large Language Model Preference Alignment Parametric Knowledge Forced Alignment Token Alignment
Enhancing Large Language Models' Situated Faithfulness to External Contexts
Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra
Large Language Model Context Information High Confidence Faithfulness Test
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu
Large Language Model Absolute Stance Bias Long Context Distance Matter Long Input Relevant Information Position Bias
Do LLMs estimate uncertainty well in instruction-following?
Juyeon Heo, Miao Xiong, Christina Heinze-Deml, Jaya Narain
Large Language Model High Uncertainty Anticipation Instruction Tuning Uncertainty Estimation Instruction Following
Large Language Models Are Overparameterized Text Encoders
Thennal D K, Tim Fischer, Chris Biemann
Large Language Model Neural Network Contrastive Training
Understanding the difficulty of low-precision post-training quantization of large language models
Zifei Xu, Sayeh Sharify, Wanzin Yazar, Tristan Webb, Xin Wang
Large Language Model Fine Tuning Post Training Quantization Difficulty Level
When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs
Hanna Kim, Minkyoo Song, Seung Ho Na, Seungwon Shin, Kimin Lee
Large Language Model LLM Agent Online Service Cyber Attack Malicious User New Threat Spear Phishing
Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
Frederic Kirstein, Terry Ruas, Robert Kratel, Bela Gipp
Large Language Model Personalized Subject Contextual Understanding Meeting Summarization
Enabling Scalable Evaluation of Bias Patterns in Medical LLMs
Hamed Fayyaz, Raphael Poulain, Rahmatollah Beheshti
Large Language Model Knowledge Graph Bias Evaluation LLM Based Evaluation BiOmedical Ontology Medical Large Language Model Large Scale Evaluation
Combining Entropy and Matrix Nuclear Norm for Enhanced Evaluation of Language Models
James Vo
Large Language Model Language Model Evaluation Metric Covariance Matrix Shannon Entropy Novel Evaluation Nuclear Norm
A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference
You Wu, Haoyi Wu, Kewei Tu
Large Language Model LLM Inference Efficient Inference Key Value Cache Systematic Study Cross Layer
Analyzing Context Utilization of LLMs in Document-Level Translation
Wafaa Mohammed, Vlad Niculae
Large Language Model Medical LLM Translation Quality Document Level Pronoun Translation Cross File Context Context Utilization
CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic
Huaiyuan Yao, Longchao Da, Vishnu Nandam, Justin Turnau, Zhiwei Liu, Linsey Pang, Hua Wei
Large Language Model Reinforcement Learning Autonomous Vehicle Mixed Autonomy Traffic
Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation
Edward (Ted) Kwartler, Matthew Berman, Alan Aqrawi
Large Language Model Artificial Intelligence Model Generated Content Faulty Negative Mitigation Language Model Hallucination
Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement
Zihao Cheng, Li Zhou, Feng Jiang, Benyou Wang, Haizhou Li
Large Language Model Text Detection LLM Generated Binary Code Content Generation Engagement Measurement Role Mining
Revisiting SLO and Goodput Metrics in LLM Serving
Zhibin Wang, Shipeng Li, Yuhang Zhou, Xue Li, Rong Gu, Nguyen Cam-Tu, Chen Tian, Sheng Zhong
Large Language Model Unified Framework LLM Inference Quality Metric LLM Generated Solution
Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
Shuo Tang, Xianghe Pang, Zexi Liu, Bohan Tang, Rui Ye, Xiaowen Dong, Yanfeng Wang, Siheng Chen
Large Language Model Multi Agent Instruction Generation

Large Language Model

Papers

AutoFPDesigner: Automated Flight Procedure Design Based on Multi-Agent Large Language Model

LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model

SPRIG: Improving Large Language Model Performance by System Prompt Optimization

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment

Enhancing Large Language Models' Situated Faithfulness to External Contexts

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs

Do LLMs estimate uncertainty well in instruction-following?

Large Language Models Are Overparameterized Text Encoders

Understanding the difficulty of low-precision post-training quantization of large language models

When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs

Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization

Enabling Scalable Evaluation of Bias Patterns in Medical LLMs

Combining Entropy and Matrix Nuclear Norm for Enhanced Evaluation of Language Models

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

Analyzing Context Utilization of LLMs in Document-Level Translation

CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic

Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation

Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement

Revisiting SLO and Goodput Metrics in LLM Serving

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation