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

November 16, 2024

Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons
Jiao Liu, Zhu Sun, Shanshan Feng, Yew-Soon Ong
Large Language Model New Benchmark Recommender System Evolutionary Algorithm Evolutionary Computation Algorithm Design
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
Huaqin Zhao, Jiaxi Li, Yi Pan, Shizhe Liang, Xiaofeng Yang, Wei Liu, Xiang Li, Fei Dou, Tianming Liu, Jin Lu
Large Language Model Parameter Efficient Fine Tuning Hessian Matrix LLM Fine Tuning Zeroth Order High Dimensional Clipping Spatial Annealing Smoothing
Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines
Yixiang Chen, Xinyu Zhang, Jinran Wang, Xurong Xie, Nan Yan, Hui Chen, Lan Wang
Large Language Model Dialogue System Mental Health Multi Turn Dialogue Dialogue Flow

November 15, 2024

Leveraging large language models for efficient representation learning for entity resolution
Xiaowei Xu, Bi T. Foua, Xingqiao Wang, Vivek Gunasekaran, John R. Talburt
Large Language Model Representation Learning Entity Matching Entity Resolution Inverse Document Frequency
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, Yingyan Celine Lin
Large Language Model High Efficiency Real World Application Real Time Deployment Accuracy Efficiency Trade
Efficient Alignment of Large Language Models via Data Sampling
Amrit Khera, Rajat Ghosh, Debojyoti Dutta
Large Language Model LLM Alignment Alignment Approach Data Sampling
On the Privacy Risk of In-context Learning
Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot, Franziska Boenisch
Large Language Model Context Learning Shot Learning Membership Inference Attack Privacy Risk Natural Language Prompt
Number it: Temporal Grounding Videos like Flipping Manga
Yongliang Wu, Xinting Hu, Yuyang Sun, Yizhou Zhou, Wenbo Zhu, Fengyun Rao, Bernt Schiele, Xu Yang
Large Language Model Numerical Data Visual Understanding Temporal Grounding Video Content Video Temporal Grounding
Scaling Law for Post-training after Model Pruning
Xiaodong Chen, Yuxuan Hu, Jing Zhang, Xiaokang Zhang, Cuiping Li, Hong Chen
Large Language Model Transformer Architecture Scaling Law Model Pruning Post Training Depth Pruning
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
Michael Aerni, Javier Rando, Edoardo Debenedetti, Nicholas Carlini, Daphne Ippolito, Florian Tramèr
Large Language Model Language Model Training Data Limited Memorization Adversarial Imitation
Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking
Valeria Jannelli, Stefan Schoepf, Matthias Bickel, Torbjørn Netland, Alexandra Brintrup
Large Language Model Consensus Group Decision Supply Chain Autonomous LLM
Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions
Yutao Hou, Yajing Luo, Zhiwen Ruan, Hongru Wang, Weifeng Ge, Yun Chen, Guanhua Chen
Large Language Model New Benchmark Evaluation Benchmark Question Decomposition
Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention
Libo Wang
Large Language Model Synthetic Data Transformer Architecture Training Model Encoder Only Transformer Visual Sycophancy
Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity
Zichen Song, Sitan Huang, Yuxin Wu, Zhongfeng Kang
Large Language Model Multi Layer Activation Sparsity Hallucination Evaluation
Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?
Yan Hu, Xu Zuo, Yujia Zhou, Xueqing Peng, Jimin Huang, Vipina K. Keloth, Vincent J. Zhang, Ruey-Ling Weng, Qingyu Chen, Xiaoqian Jiang, Kirk E. Roberts, Hua Xu
Large Language Model Natural Language Processing Entity Recognition Information Extraction Clinical Note Annotated Corpus Clinical Named Entity Recognition
Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
Taaha Kazi, Ruiliang Lyu, Sizhe Zhou, Dilek Hakkani-Tur, Gokhan Tur
Large Language Model Context Example Task Oriented Dialogue System Conversational System Context Awareness Task Performance User Agent

November 14, 2024

Squeezed Attention: Accelerating Long Context Length LLM Inference
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, June Paik, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
Large Language Model Long Context Long Context Large Language Model Long Input Long Context Benchmark
LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
Zhengyi Wang, Jonathan Lorraine, Yikai Wang, Hang Su, Jun Zhu, Sanja Fidler, Xiaohui Zeng
Large Language Model Language Model 3D Mesh LLaMA Model 3D Mesh Generation Isomorphic Mesh
Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents
Yuyou Gan, Yong Yang, Zhe Ma, Ping He, Rui Zeng, Yiming Wang, Qingming Li, Chunyi Zhou, Songze Li, Ting Wang, Yunjun Gao, Yingcai Wu, Shouling Ji
Large Language Model Transformer Based Model Agent Smith NLP Field Privacy Policy Security Related Risk Sensitive Multi Agent Scenario Ethical Risk
MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs
Mengyuan Zhang, Ruihui Wang, Bo Xia, Yuan Sun, Xiaobing Zhao
Large Language Model Language Understanding Low Resource Language High Resource Language G Eval Semantic Task

Large Language Model

Papers

Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons

HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization

Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines

Leveraging large language models for efficient representation learning for entity resolution

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

Efficient Alignment of Large Language Models via Data Sampling

On the Privacy Risk of In-context Learning

Number it: Temporal Grounding Videos like Flipping Manga

Scaling Law for Post-training after Model Pruning

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models

Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking

Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions

Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention

Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity

Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems

Squeezed Attention: Accelerating Long Context Length LLM Inference

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

MM-Eval: A Hierarchical Benchmark for Modern Mongolian Evaluation in LLMs