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

December 6, 2024

Smoothie: Label Free Language Model Routing
Neel Guha, Mayee F. Chen, Trevor Chow, Ishan S. Khare, Christopher Ré
Large Language Model Ground Truth FRUIT Produce SMOOTHIE

December 5, 2024

Improving LLM Group Fairness on Tabular Data via In-Context Learning
Valeriia Cherepanova, Chia-Jung Lee, Nil-Jana Akpinar, Riccardo Fogliato, Martin Andres Bertran, Michael Kearns, James Zou
Large Language Model Context Learning Tabular Data Group Fairness Prompt Optimization Debiasing Method Structure Fairness
Give me Some Hard Questions: Synthetic Data Generation for Clinical QA
Fan Bai, Keith Harrigian, Joel Stremmel, Hamid Hassanzadeh, Ardavan Saeedi, Mark Dredze
Large Language Model Synthetic Data Generation Question Generation Medical Question Answering Complex Question Medical Question Answering System
EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios
Lu Qiu, Yuying Ge, Yi Chen, Yixiao Ge, Ying Shan, Xihui Liu
Large Language Model Language Model New Benchmark Multimodal Large Language Model Real World Scenario Real World Planning Planning Perspective
Understanding Hidden Computations in Chain-of-Thought Reasoning
Aryasomayajula Ram Bharadwaj
Large Language Model Transformer Model Chain of Thought Complex Reasoning Task Privacy Preserving Computation
Retrieval-Augmented Machine Translation with Unstructured Knowledge
Jiaan Wang, Fandong Meng, Yingxue Zhang, Jie Zhou
Large Language Model Machine Translation Retrieval Augmented Generation Unstructured Data
Liquid: Language Models are Scalable Multi-modal Generators
Junfeng Wu, Yi Jiang, Chuofan Ma, Yuliang Liu, Hengshuang Zhao, Zehuan Yuan, Song Bai, Xiang Bai
Large Language Model Language Model Image Generation Visual Understanding Vision Language Understanding Multi Modal Generation Liquid State Multimodal Generation Capability
The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
Fredrik Carlsson, Fangyu Liu, Daniel Ward, Murathan Kurfali, Joakim Nivre
Large Language Model Model Overfitting Pre Trained Large Language Model Open Ended Text Generation Generative Capability Generalization Characteristic
FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression
Bo Tong, Bokai Lai, Yiyi Zhou, Gen Luo, Yunhang Shen, Ke Li, Xiaoshuai Sun, Rongrong Ji
Large Language Model Multimodal Large Language Model TinyML Model Visual Token Multimodal Capability
Densing Law of LLMs
Chaojun Xiao, Jie Cai, Weilin Zhao, Guoyang Zeng, Xu Han, Zhiyuan Liu, Maosong Sun
Large Language Model Open Source Large Language Model Particle Density Effective Parameter
ALMA: Alignment with Minimal Annotation
Michihiro Yasunaga, Leonid Shamis, Chunting Zhou, Andrew Cohen, Jason Weston, Luke Zettlemoyer, Marjan Ghazvininejad
Large Language Model Alignment Problem Selective Annotation Large Scale Learning Response Generation Model
Evolutionary Pre-Prompt Optimization for Mathematical Reasoning
Mathurin Videau, Alessandro Leite, Marc Schoenauer, Olivier Teytaud
Large Language Model Shot Learning Chain of Thought Mathematical Reasoning Complex Reasoning Task Prompt Optimization
AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic
Nathaniel R. Robinson, Shahd Abdelmoneim, Kelly Marchisio, Sebastian Ruder
Large Language Model LLM Performance Language Technology Accuracy Measurement Dialect Speaker
Leveraging Large Language Models to Generate Course-specific Semantically Annotated Learning Objects
Dominic Lohr, Marc Berges, Abhishek Chugh, Michael Kohlhase, Dennis Müller
Large Language Model Generative Language Model Question Generation Semantic Annotation Learner Model Learning Resource
Monet: Mixture of Monosemantic Experts for Transformers
Jungwoo Park, Young Jin Ahn, Kee-Eung Kim, Jaewoo Kang
Large Language Model Transformer Megatron Decepticons Mixture Component Mechanistic Interpretability Sparse Autoencoders Revisit Monosemanticity
Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
Yuhao Wang, Junwei Pan, Xiangyu Zhao, Pengyue Jia, Wanyu Wang, Yuan Wang, Yue Liu, Dapeng Liu, Jie Jiang
Large Language Model Sequential Recommendation Text Embeddings Recommendation Model LD Align Disentangle Content
Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models
Eyad Gomaa, Gomaa Salah
Large Language Model Full Model Complex Reasoning Reasoning Capability Large Language Reasoning Path Human Guidance AI Reasoning
Practical Considerations for Agentic LLM Systems
Chris Sypherd, Vaishak Belle
Large Language Model LLM Based LLM Agent
LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents
Bingchen Li, Xin Li, Yiting Lu, Zhibo Chen
Large Language Model Loss Function Image Processing Optimization Objective
MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
Changcheng Li, Xiangyu Wang, Qiuju Chen, Xiren Zhou, Huanhuan Chen
Large Language Model Medical LLM Higher Order Multi Step Tree of Thought Dual Thinking

Large Language Model

Papers

Smoothie: Label Free Language Model Routing

Improving LLM Group Fairness on Tabular Data via In-Context Learning

Give me Some Hard Questions: Synthetic Data Generation for Clinical QA

EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios

Understanding Hidden Computations in Chain-of-Thought Reasoning

Retrieval-Augmented Machine Translation with Unstructured Knowledge

Liquid: Language Models are Scalable Multi-modal Generators

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation

FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression

Densing Law of LLMs

ALMA: Alignment with Minimal Annotation

Evolutionary Pre-Prompt Optimization for Mathematical Reasoning

AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic

Leveraging Large Language Models to Generate Course-specific Semantically Annotated Learning Objects

Monet: Mixture of Monosemantic Experts for Transformers

Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models

Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models

Practical Considerations for Agentic LLM Systems

LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM