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 18, 2024

Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework
Zhen Tao, Zhiyu Li, Runyu Chen, Dinghao Xi, Wei Xu
Large Language Model Fine Grained Sentence Level LLM Generated Linguistic Feature Plagiarism Detection
Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning
Pengfei He, Zitao Li, Yue Xing, Yaling Li, Jiliang Tang, Bolin Ding
Large Language Model Zero Shot Complex Reasoning Multi Agent Multi Step Reasoning Reasoning Strategy
LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
Yujun Zhou, Jingdong Yang, Kehan Guo, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang
Large Language Model Human SAFETY Safety Guarantee Likely LAB of Origin Safety Benchmark
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Huazheng Wang, Kaixuan Huang, Yue Wu, Mengdi Wang
Large Language Model Preference Optimization Temporal Alignment Tree Search Best of N
Automated Genre-Aware Article Scoring and Feedback Using Large Language Models
Chihang Wang, Yuxin Dong, Zhenhong Zhang, Ruotong Wang, Shuo Wang, Jiajing Chen
Large Language Model Full Model Human Feedback Large Language News Classification Feature Mining
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
Chenyang Zhang, Jiayi Lin, Haibo Tong, Bingxuan Hou, Dongyu Zhang, Jialin Li, Junli Wang
Large Language Model Language Model Text Generation Instruction Tuning

October 17, 2024

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao
Large Language Model Medical LLM Individual Representation Long Term Memory Memory Augmentation
Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection
Chuhong Mai, Ro-ee Tal, Thahir Mohamed
Large Language Model Context Learning Agnostic Representation Task Specific Representation Relevant Question Context Dependent Text to SQL
Best in Tau@LLMJudge: Criteria-Based Relevance Evaluation with Llama3
Naghmeh Farzi, Laura Dietz
Large Language Model Relevance Ranking Relevance Prediction Relevance Label
Efficient Retrieval of Temporal Event Sequences from Textual Descriptions
Zefang Liu, Yinzhu Quan
Large Language Model Text Modality Natural Language Description Description Library Event Sequence Efficient Retrieval Temporal Sequence Sequence Representation
LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education
Iain Weissburg, Sathvika Anand, Sharon Levy, Haewon Jeong
Large Language Model Inherent Bias LLM Bias Bias Score Source Bias Personalized Education
Detecting AI-Generated Texts in Cross-Domains
You Zhou, Jie Wang
Large Language Model Training Data Data Detection Cross Domain Text Based RoBERTa Model
Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models
Eddie L. Ungless, Nikolas Vitsakis, Zeerak Talat, James Garforth, Björn Ross, Arno Onken, Atoosa Kasirzadeh, Alexandra Birch
Large Language Model Full Model Large Language Ethical Consideration Research Ethic White Paper Ethic Dataset
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
Lijie Fan, Tianhong Li, Siyang Qin, Yuanzhen Li, Chen Sun, Michael Rubinstein, Deqing Sun, Kaiming He, Yonglong Tian
Large Language Model Language Model Text to Image Generation Autoregressive Model Fluid Dynamic
Retrospective Learning from Interactions
Zizhao Chen, Mustafa Omer Gul, Yiwei Chen, Gloria Geng, Anne Wu, Yoav Artzi
Large Language Model Interaction Strategy Implicit Feedback Abstract Reasoning Multimodal Interaction Retrospective Learning
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction
Xuan Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin
Large Language Model Long Context Large Language Model Key Value Cache Key Value Cache Compression
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs
Tianyu Guo, Druv Pai, Yu Bai, Jiantao Jiao, Michael I. Jordan, Song Mei
Large Language Model K TOKEN Transformer Based Large Language Model Attention Head Mechanistic Study Anomalous Token
BenTo: Benchmark Task Reduction with In-Context Transferability
Hongyu Zhao, Ming Li, Lichao Sun, Tianyi Zhou
Large Language Model Context Learning LLM Benchmark LLM Output Benchmark Task
Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions
Michael J.Q. Zhang, W. Bradley Knox, Eunsol Choi
Large Language Model Yes No Question Open Domain Question LLM Response User Understanding Preference Label
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
Zekun Moore Wang, Shawn Wang, Kang Zhu, Jiaheng Liu, Ke Xu, Jie Fu, Wangchunshu Zhou, Wenhao Huang
Large Language Model Alignment Problem Preference Pair Model Alignment Contrastive Pair Distinct Pattern

Large Language Model

Papers

Unveiling Large Language Models Generated Texts: A Multi-Level Fine-Grained Detection Framework

Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning

LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Automated Genre-Aware Article Scoring and Feedback Using Large Language Models

A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection

Best in Tau@LLMJudge: Criteria-Based Relevance Evaluation with Llama3

Efficient Retrieval of Temporal Event Sequences from Textual Descriptions

LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education

Detecting AI-Generated Texts in Cross-Domains

Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Retrospective Learning from Interactions

SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction

Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

BenTo: Benchmark Task Reduction with In-Context Transferability

Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment