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 11, 2024

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
Kirti Bhagat, Kinshuk Vasisht, Danish Pruthi
Large Language Model Language Model Health Disparity
Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving
Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb, Boyu Gou, Daniel Adu-Ampratwum, Xia Ning, Huan Sun
Large Language Model Global Impact Language Agent Easy Tool Organic Chemistry Chemical Domain Knowledge Chemical Named Entity Recognition
Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks
Madeline Brumley, Joe Kwon, David Krueger, Dmitrii Krasheninnikov, Usman Anwar
Large Language Model Inherent Interpretability Constructive Approach Different Context Interpretability Research Learning Task Steering Vector Context Vector Bottom Up Framework
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Radha Poovendran
Large Language Model Instruction Tuning Response Generation Instruction Following Good Teacher Strong Model Synthetic Instruction Data
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
Taihang Hu, Linxuan Li, Joost van de Weijer, Hongcheng Gao, Fahad Shahbaz Khan, Jian Yang, Ming-Ming Cheng, Kai Wang, Yaxing Wang
Large Language Model Text to Image Complex Prompt Critical Synthesis Semantic Structure Token Merging Symbol Binding Concept Learner
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Ruben Härle, Felix Friedrich, Manuel Brack, Björn Deiseroth, Patrick Schramowski, Kristian Kersting
Large Language Model Text Generation Supervised Autoencoder Many Sparse Human Like Steering Technique Toxic Comment Concept Detection
LongSafetyBench: Long-Context LLMs Struggle with Safety Issues
Mianqiu Huang, Xiaoran Liu, Shaojun Zhou, Mozhi Zhang, Chenkun Tan, Pengyu Wang, Qipeng Guo, Zhe Xu, Linyang Li, Zhikai Lei, Linlin Li, Qun Liu, Yaqian Zhou, Xipeng Qiu, Xuanjing Huang
Large Language Model Long Context Human SAFETY Long Context Large Language Model Long Context Language Long Context Scenario
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Junho Kim, Hyungjin Chung, Byung-Hoon Kim
Large Language Model Arbitrary Object Customer Service Multimodal Chart Category Agnostic Pose
1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs
Jebish Purbey, Siddartha Pullakhandam, Kanwal Mehreen, Muhammad Arham, Drishti Sharma, Ashay Srivastava, Ram Mohan Rao Kadiyala
Large Language Model Natural Language Processing Data Detection Medical LLM Transformer Model Hate Speech NLU Model Indic Script Language Detection
LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models
Runming Yang, Taiqiang Wu, Jiahao Wang, Pengfei Hu, Ngai Wong, Yujiu Yang
Large Language Model Knowledge Distillation Full Model Knowledge Transfer Large Language
Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding
Zeyd Boukhers, AmeerAli Khan, Qusai Ramadan, Cong Yang
Large Language Model Text Representation Medical Text Medical Coding ICD Code Classification Application Health Informatics
Large-scale moral machine experiment on large language models
Muhammad Shahrul Zaim bin Ahmad, Kazuhiro Takemoto
Large Language Model Human Moral Moral Machine Moral Decision
PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing
Yiwen Duan, Yonghong Yu, Xiaoming Zhao, Yichang Wu, Wenbo Liu
Large Language Model Built Road Code LLM Dataset Creation DeepSeek Coder
Reverse Prompt Engineering
Hanqing Li, Diego Klabjan
Large Language Model Language Model Automatic Prompt Engineering Zero Shot Language

November 10, 2024

vTune: Verifiable Fine-Tuning for LLMs Through Backdooring
Eva Zhang, Arka Pal, Akilesh Potti, Micah Goldblum
Large Language Model Native Robustness Fine Tuning Backdoor Attack Closed Source Model
Epistemic Integrity in Large Language Models
Bijean Ghafouri, Shahrad Mohammadzadeh, James Zhou, Pratheeksha Nair, Jacob-Junqi Tian, Mayank Goel, Reihaneh Rabbany, Jean-François Godbout, Kellin Pelrine
Large Language Model Training Data Epistemic Uncertainty Trustworthy Artificial Intelligence Epistemic Space
Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs
Kazuki Fujii, Taishi Nakamura, Rio Yokota
Large Language Model Natural Language Model Performance Large Scale Model Balance Control FP8 Format
Hermes: A Large Language Model Framework on the Journey to Autonomous Networks
Fadhel Ayed, Ali Maatouk, Nicola Piovesan, Antonio De Domenico, Merouane Debbah, Zhi-Quan Luo
Large Language Model Network Programming Autonomous System Legal Autonomy Network Model Network Intelligence Autonomous Network
ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?
Canyu Chen, Jian Yu, Shan Chen, Che Liu, Zhongwei Wan, Danielle Bitterman, Fei Wang, Kai Shu
Large Language Model Machine Learning Model Human Prediction Medical Benchmark Clinical Language Clinical Prediction Task Clinical Prediction Model
Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator
Kazuki Fujii, Kohei Watanabe, Rio Yokota
Large Language Model Pipeline Parallelism Large Language Model Training Expert Parallelism Tensor Parallelism 3D Parallelism Sequence Parallelism

Large Language Model

Papers

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations

Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving

Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis

SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs

LongSafetyBench: Long-Context LLMs Struggle with Safety Issues

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs

LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models

Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding

Large-scale moral machine experiment on large language models

PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing

Reverse Prompt Engineering

vTune: Verifiable Fine-Tuning for LLMs Through Backdooring

Epistemic Integrity in Large Language Models

Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs

Hermes: A Large Language Model Framework on the Journey to Autonomous Networks

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator