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

September 27, 2024

Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning
Arshiya Khan, Guannan Liu, Xing Gao
Large Language Model Prompt Tuning Software Vulnerability Vulnerable Code Vulnerability Repair

September 26, 2024

LowREm: A Repository of Word Embeddings for 87 Low-Resource Languages Enhanced with Multilingual Graph Knowledge
Daniil Gurgurov, Rishu Kumar, Simon Ostermann
Large Language Model Jina Embeddings Low Resource Language Word Embeddings Static Word Embeddings Repository Scale Multilingual Knowledge Graph
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
Ye Liu, Zongyang Ma, Zhongang Qi, Yang Wu, Ying Shan, Chang Wen Chen
Large Language Model Video Understanding Video Understanding Benchmark Video Language Understanding
Data-Prep-Kit: getting your data ready for LLM application development
David Wood, Boris Lublinsky, Alexy Roytman, Shivdeep Singh, Abdulhamid Adebayo, Revital Eres, Mohammad Nassar, Hima Patel, Yousaf Shah, Constantin Adam, Petros Zerfos, Nirmit Desai, Daiki Tsuzuku, Takuya Goto, Michele Dolfi, Saptha Surendran, Paramesvaran Selvam, Sungeun An, Yuan Chi Chang, Dhiraj Joshi, Hajar Emami-Gohari, Xuan-Hong Dang, Yan Koyfman, Shahrokh Daijavad
Large Language Model Raw Data Retrieval Augmented Generation Data Preparation
Compositional Hardness of Code in Large Language Models -- A Probabilistic Perspective
Yotam Wolf, Binyamin Rothberg, Dorin Shteyman, Amnon Shashua
Large Language Model Real World Code Bayesian Perspective Hardness Result Long Form Generation Subtask Assignment
Role-RL: Online Long-Context Processing with Role Reinforcement Learning for Distinct LLMs in Their Optimal Roles
Lewei He, Tianyu Shi, Pengran Huang, Bingzhi Chen, Qianglong Chen, Jiahui Pan
Large Language Model Integral Role Long Context Role Based Dynamic Role
LLM4Brain: Training a Large Language Model for Brain Video Understanding
Ruizhe Zheng, Lichao Sun
Large Language Model Video Understanding Multimodal Information fMRI Signal FMRI Encoding
Weak-to-Strong Backdoor Attack for Large Language Models
Shuai Zhao, Leilei Gan, Zhongliang Guo, Xiaobao Wu, Luwei Xiao, Xiaoyu Xu, Cong-Duy Nguyen, Luu Anh Tuan
Large Language Model Backdoor Attack
Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect
Guokan Shang, Hadi Abdine, Yousef Khoubrane, Amr Mohamed, Yassine Abbahaddou, Sofiane Ennadir, Imane Momayiz, Xuguang Ren, Eric Moulines, Preslav Nakov, Michalis Vazirgiannis, Eric Xing
Large Language Model High Resource Language
Graph Reasoning with Large Language Models via Pseudo-code Prompting
Konstantinos Skianis, Giannis Nikolentzos, Michalis Vazirgiannis
Large Language Model Natural Language Processing Graph Reasoning Graph Level Task Graph Problem
Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy
Owen Henkel, Hannah Horne-Robinson, Maria Dyshel, Nabil Ch, Baptiste Moreau-Pernet, Ralph Abood
Large Language Model LeArning Abstract MAESTRO Dataset Question Answer Pair Public Exception Learning Arithmetic Formative Assessment
EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Shaoxiong Ji, Zihao Li, Indraneil Paul, Jaakko Paavola, Peiqin Lin, Pinzhen Chen, Dayyán O'Brien, Hengyu Luo, Hinrich Schütze, Jörg Tiedemann, Barry Haddow
Large Language Model Cross Lingual Transfer Cross Lingual Multilingual Dataset Multilingual Large Language Model Cross Lingual Performance
Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores
Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang
Large Language Model LLM Inference Matrix Multiplication Tensor Core
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Hui-Po Wang, Mario Fritz
Large Language Model Language Model Gradient Compression Network Prior Neural Network Gradient
PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification
Tianfang Xie, Tianjing Li, Wei Zhu, Wei Han, Yi Zhao
Large Language Model Parameter Efficient Fine Tuning Semantic Description Controllable Generation Multi Tenant
Inference-Time Language Model Alignment via Integrated Value Guidance
Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang, Chao Yang, Yu Qiao
Large Language Model Language Model Value Function Language Model Alignment Multi Concept Guidance Sentiment Expression
Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT
Natthanaphop Isaradech, Andrea Riedel, Wachiranun Sirikul, Markus Kreuzthaler, Stefan Schulz
Large Language Model ChatGPT Generated Conversation Entity Recognition Clinical Note Better Zero Drug Classification Free Text Clinical Drug Safety Text Expansion
Data Proportion Detection for Optimized Data Management for Large Language Models
Hao Liang, Keshi Zhao, Yajie Yang, Bin Cui, Guosheng Dong, Zenan Zhou, Wentao Zhang
Large Language Model
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Xuefeng Du, Chaowei Xiao, Yixuan Li
Large Language Model Hallucination Detection Based Telescope
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
Yuqing Zhou, Ruixiang Tang, Ziyu Yao, Ziwei Zhu
Large Language Model Language Model Text Classification Comprehensive Analysis Shortcut Learning Shortcut Feature Maze Environment Shortcut Pattern Avoidance Loss

Large Language Model

Papers

Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning

LowREm: A Repository of Word Embeddings for 87 Low-Resource Languages Enhanced with Multilingual Graph Knowledge

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

Data-Prep-Kit: getting your data ready for LLM application development

Compositional Hardness of Code in Large Language Models -- A Probabilistic Perspective

Role-RL: Online Long-Context Processing with Role Reinforcement Learning for Distinct LLMs in Their Optimal Roles

LLM4Brain: Training a Large Language Model for Brain Video Understanding

Weak-to-Strong Backdoor Attack for Large Language Models

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

Graph Reasoning with Large Language Models via Pseudo-code Prompting

Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy

EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models

PEDRO: Parameter-Efficient Fine-tuning with Prompt DEpenDent Representation MOdification

Inference-Time Language Model Alignment via Integrated Value Guidance

Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT

Data Proportion Detection for Optimized Data Management for Large Language Models

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models