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 8, 2024

Insights from Benchmarking Frontier Language Models on Web App Code Generation
Yi Cui
Large Language Model Language Model Code Generation DCU Insight AQ Real World Code Error Mitigation Model Reliability
OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang
Large Language Model High Efficiency NLP Task App to App Retrieval Retrieval Task Generation Model

September 7, 2024

Achieving Peak Performance for Large Language Models: A Systematic Review
Zhyar Rzgar K Rostam, Sándor Szénási, Gábor Kertész
Large Language Model Natural Language Processing Systematic Review LLM Inference Enhancing Efficiency
MILE: A Mutation Testing Framework of In-Context Learning Systems
Zeming Wei, Yihao Zhang, Meng Sun
Large Language Model Context Learning Context Demonstration New Embeddings Mutation Testing
POINTS: Improving Your Vision-language Model with Affordable Strategies
Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang, Le Tian, Xiao Zhou, Jie Zhou
Large Language Model Vision Language Model Exceptional Point Open Source Model Visual Instruction Tuning Model Soup
Exploring Straightforward Conversational Red-Teaming
George Kour, Naama Zwerdling, Marcel Zalmanovici, Ateret Anaby-Tavor, Ora Nova Fandina, Eitan Farchi
Large Language Model Red Teaming Multi Turn Conversation Spoken Dialogue System
TracrBench: Generating Interpretability Testbeds with Large Language Models
Hannes Thurnherr, Jérémy Scheurer
Large Language Model Transformer Based Language Model Interpretability Method Interpretability Analysis Robotic Assembly Sequence Planning
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models
Junfeng Tian, Da Zheng, Yang Cheng, Rui Wang, Colin Zhang, Debing Zhang
Large Language Model Language Model Long Context Knot Theory
Good Idea or Not, Representation of LLM Could Tell
Yi Xu, Bo Xue, Shuqian Sheng, Cheng Deng, Jiaxin Ding, Zanwei Shen, Luoyi Fu, Xinbing Wang, Chenghu Zhou
Large Language Model Medical LLM Individual Representation Human Generated Idea Text Evaluation Generative Model Output

September 6, 2024

Sparse Rewards Can Self-Train Dialogue Agents
Barrett Martin Lattimer, Varun Gangal, Ryan McDonald, Yi Yang
Large Language Model Human Feedback Sparse Reward Multi Turn Dialogue Sparse Reward Environment
Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning
Xinyue Liu, Harshita Diddee, Daphne Ippolito
Large Language Model Adaptation Concern Parameter Efficient Finetuning Real Time Customization
How Does Code Pretraining Affect Language Model Task Performance?
Jackson Petty, Sjoerd van Steenkiste, Tal Linzen
Large Language Model Language Model Natural Language Compositional Task
Evaluating the Impact of a Specialized LLM on Physician Experience in Clinical Decision Support: A Comparison of Ask Avo and ChatGPT-4
Daniel Jung, Alex Butler, Joongheum Park, Yair Saperstein
Large Language Model Medical LLM Clinical Decision Support Clinical Decision Support System Internal Medicine DOCTOR ChatGPT 4
RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs
Jiaxing Wu, Lin Ning, Luyang Liu, Harrison Lee, Neo Wu, Chao Wang, Sushant Prakash, Shawn O'Banion, Bradley Green, Jun Xie
Large Language Model Reinforcement Learning LLM Personalization Personalized Summarization
Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs
Aliakbar Nafar, Kristen Brent Venable, Parisa Kordjamshidi
Large Language Model LeArning Abstract Context Learning App to App Retrieval Novel Regression Generative Large Language Model Context Example Retrieval System Context Learner
Cognitive phantoms in LLMs through the lens of latent variables
Sanne Peereboom, Inga Schwabe, Bennett Kleinberg
Large Language Model Camera Lens Latent Variable Human Like Latent Variable Model Psychometric Property Polyp Phantom
GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding
Ziyin Zhang, Hang Yu, Shijie Li, Peng Di, Jianguo Li, Rui Wang
Large Language Model Graph Drawing Graph Data Code Language Model Code LLM
From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks
Andreas Stephan, Dawei Zhu, Matthias Aßenmacher, Xiaoyu Shen, Benjamin Roth
Large Language Model Multi Step Reasoning LLM a a Judge Mathematical Reasoning Task Different Calculation Method Candidate Retrieval
Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation
Luis Mayer, Christian Heumann, Matthias Aßenmacher
Large Language Model ChatGPT Generated Conversation Comparative Study Code Generation Faithful Generation Real World Code Open Source Code Model
Multi-Programming Language Ensemble for Code Generation in Large Language Model
Tengfei Xue, Xuefeng Li, Tahir Azim, Roman Smirnov, Jianhui Yu, Arash Sadrieh, Babak Pahlavan
Large Language Model Code Generation

Large Language Model

Papers

Insights from Benchmarking Frontier Language Models on Web App Code Generation

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

Achieving Peak Performance for Large Language Models: A Systematic Review

MILE: A Mutation Testing Framework of In-Context Learning Systems

POINTS: Improving Your Vision-language Model with Affordable Strategies

Exploring Straightforward Conversational Red-Teaming

TracrBench: Generating Interpretability Testbeds with Large Language Models

Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models

Good Idea or Not, Representation of LLM Could Tell

Sparse Rewards Can Self-Train Dialogue Agents

Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning

How Does Code Pretraining Affect Language Model Task Performance?

Evaluating the Impact of a Specialized LLM on Physician Experience in Clinical Decision Support: A Comparison of Ask Avo and ChatGPT-4

RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs

Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs

Cognitive phantoms in LLMs through the lens of latent variables

GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding

From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks

Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation

Multi-Programming Language Ensemble for Code Generation in Large Language Model