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 22, 2024

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models
Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang
Large Language Model Full Model K TOKEN Visual Token Video Language Temporal Shift Module Complex Video
ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data
Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar
Large Language Model Open Source LLM Production Incident Web Agent Process Data General Purpose LLM
GOT4Rec: Graph of Thoughts for Sequential Recommendation
Zewen Long, Liang Wang, Shu Wu, Qiang Liu, Liang Wang
Large Language Model Graph Drawing Sequential Recommendation User Behavior Thought Reasoning Prompt Based Learning
ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos
Tanveer Hannan, Md Mohaiminul Islam, Jindong Gu, Thomas Seidl, Gedas Bertasius
Large Language Model Vision Language Model Long Video Temporal Grounding
Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts
Anna Glazkova, Olga Zakharova
Large Language Model Data Augmentation Classification Code Natural Language NLP Field Multi Label LLM Prompt Prompt Augmentation
KBAlign: Efficient Self Adaptation on Specific Knowledge Bases
Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
Large Language Model Knowledge Base Annotated Dataset LLM Annotation Knowledge Adaptation
Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Jiashuo Liang, Guancheng Li, Yang Yu
Large Language Model Medical LLM Structured Output Gradient Based Attack Precision Control
LIBER: Lifelong User Behavior Modeling Based on Large Language Models
Chenxu Zhu, Shigang Quan, Bo Chen, Jianghao Lin, Xiaoling Cai, Hong Zhu, Xiangyang Li, Yunjia Xi, Weinan Zhang, Ruiming Tang
Large Language Model Language Model Recommendation Model User Behavior LLM Based Recommender System
Understanding LLM Embeddings for Regression
Eric Tang, Bangding Yang, Xingyou Song
Large Language Model High Dimensional Novel Regression LLM Embeddings
Comparative Analysis of Pooling Mechanisms in LLMs: A Sentiment Analysis Perspective
Jinming Xing, Ruilin Xing, Yan Sun
Large Language Model Natural Language Processing Sentiment Analysis Comparative Study Visual Perspective Sentence Level Token Level Sentence Level Sentiment

November 21, 2024

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings
Aaron Zheng, Mansi Rana, Andreas Stolcke
Large Language Model Fine Tuned Large Language Model Fine Tuned BERT Guardrail Model Purple LLaMA CyberSecEval Safety Benchmark
UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages
Bethel Melesse Tessema (1), Akhil Kedia (2), Tae-Sun Chung (1) ((1) Ajou University, (2) Independent Researcher)
Large Language Model Low Resource Language Monolingual Data Effective Adaptation Common Crawl Corpus
Memory Backdoor Attacks on Neural Networks
Eden Luzon, Guy Amit, Roy Weiss, Yisroel Mirsky
Large Language Model Neural Network Training Data
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D'arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, Graham Neubig, Dan Weld, Doug Downey, Wen-tau Yih, Pang Wei Koh, Hannaneh Hajishirzi
Large Language Model Language Model GPT 4
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Advik Raj Basani, Xiao Zhang
Large Language Model Black Box Jailbreak Attack Adversarial Suffix
Towards a Middleware for Large Language Models
Narcisa Guran, Florian Knauf, Man Ngo, Stefan Petrescu, Jan S. Rellermeyer
Large Language Model Natural Language Input Cloud Service Multiple Middleware
Learning from "Silly" Questions Improves Large Language Models, But Only Slightly
Tingyuan Zhu, Shudong Liu, Yidong Wang, Derek F. Wong, Han Yu, Takahiro Shinozaki, Jindong Wang
Large Language Model Yes No Question Supervised Fine Tuning Large Scale Evaluation
Enhancing Prediction Models with Reinforcement Learning
Karol Radziszewski, Piotr Ociepka
Large Language Model Reinforcement Learning Personalized Recommendation Prediction Model News Recommendation Improving Prediction
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Min Zhang, Zhaopeng Tu
Large Language Model Native Robustness Robust Optimization Structured Pruning
Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
Daehoon Gwak, Junwoo Park, Minho Park, Chaehun Park, Hyunchan Lee, Edward Choi, Jaegul Choo
Large Language Model World Event State of the Art Forecasting Event Prediction Event Model

Large Language Model

Papers

DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

GOT4Rec: Graph of Thoughts for Sequential Recommendation

ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos

Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases

Universal and Context-Independent Triggers for Precise Control of LLM Outputs

LIBER: Lifelong User Behavior Modeling Based on Large Language Models

Understanding LLM Embeddings for Regression

Comparative Analysis of Pooling Mechanisms in LLMs: A Sentiment Analysis Perspective

Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings

UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages

Memory Backdoor Attacks on Neural Networks

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

Towards a Middleware for Large Language Models

Learning from "Silly" Questions Improves Large Language Models, But Only Slightly

Enhancing Prediction Models with Reinforcement Learning

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization

Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling