LLM Model

Large language models (LLMs) are powerful AI systems designed to process and generate human-like text, enabling applications ranging from text generation and translation to complex reasoning tasks. Current research focuses on improving LLM efficiency (e.g., through quantization and optimized training techniques), addressing limitations in areas like time series forecasting and commonsense reasoning, and exploring their integration into diverse fields such as robotics, autonomous driving, and healthcare. The ability of LLMs to handle complex tasks and integrate with other systems makes them a significant tool for both scientific advancement and practical applications across numerous domains.

Papers

January 12, 2024

Adapting Large Language Models for Document-Level Machine Translation
Minghao Wu, Thuy-Trang Vu, Lizhen Qu, George Foster, Gholamreza Haffari
Large Language Model Document Level LLM Model Translation Performance

November 27, 2023

Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination
Haoqiang Kang, Xiao-Yang Liu
Large Language Model Retrieval Augmented Generation Shot Learning Empirical Study Content Hallucination Visual Hallucination LLM Model Lack Thereof

November 15, 2023

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, Jun Liu
Symbolic Knowledge LLM Model Symbol Detection Higher NLE Quality

August 9, 2023

A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology
Sean Wu, Michael Koo, Lesley Blum, Andy Black, Liyo Kao, Fabien Scalzo, Ira Kurtz
Comparative Study GPT 4 Open Source Large Language Model Multiple Choice Question LLM Model Medical Domain Knowledge Adaptive Training

August 3, 2023

Fast Slate Policy Optimization: Going Beyond Plackett-Luce
Otmane Sakhi, David Rohde, Nicolas Chopin
Action Space Policy Optimization LLM Model Large Scale Machine Learning Large Scale Decision

July 25, 2023

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu, Min Zhang
Data Augmentation Semantic Parsing Architecture Design Document Parsing Syntactic Information LLM Model Holistic Perception Universal Semantic

May 23, 2023

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
Zirui Zhao, Wee Sun Lee, David Hsu
Large Language Model Commonsense Knowledge LLM Model

February 10, 2023

Efficient and Accurate Learning of Mixtures of Plackett-Luce Models
Duc Nguyen, Anderson Y. Zhang
High Efficiency Mixture Component Maximum Likelihood Log Likelihood LLM Model EM Algorithm Accurate Learning Surrogate Likelihood

May 12, 2022

Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling
Alexander Buchholz, Jan Malte Lichtenberg, Giuseppe Di Benedetto, Yannik Stein, Vito Bellini, Matteo Ruffini
Sample Efficient Learning to Rank LLM Model Quasi Monte Carlo

LLM Model

Papers

Adapting Large Language Models for Document-Level Machine Translation

Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models

A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology

Fast Slate Policy Optimization: Going Beyond Plackett-Luce

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Efficient and Accurate Learning of Mixtures of Plackett-Luce Models

Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling