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

October 14, 2024

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning
Bokai Hu, Sai Ashish Somayajula, Xin Pan, Zihan Huang, Pengtao Xie
Large Language Model Reinforcement Learning Full Model Natural Language Language Generation Large Language NLU Model BERT Large
Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs
Abdellah El Mekki, Muhammad Abdul-Mageed
Large Language Model Natural Language Processing Machine Translation View Translation Context Example Unsupervised Model
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han
Large Language Model App to App Retrieval Long Context Long Context LLM Long Range Context
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
Ziyue Li, Tianyi Zhou
Large Language Model Full Model Mixture of Expert Representation Finetuning Task Specific Embeddings
Focused ReAct: Improving ReAct through Reiterate and Early Stop
Shuoqiu Li, Han Xu, Haipeng Chen
Large Language Model Frontend Component Code
AFlow: Automating Agentic Workflow Generation
Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, Chenglin Wu
Large Language Model Workflow Composition Process Optimization
SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization
Akrit Mudvari, Yuang Jiang, Leandros Tassiulas
Large Language Model Chatbot Response LLM Inference Worst Case User Throughput Collaborative Inference Inference Engine Model Placement
Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
Ishan Jindal, Chandana Badrinath, Pranjal Bharti, Lakkidi Vinay, Sachin Dev Sharma
Large Language Model Instruction Following Continual Pre Training Instruction Fine Tuning
Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection
Giorgos Iacovides, Wuyang Zhou, Danilo Mandic
Large Language Model Language Model High Efficiency Tensor Network Network Selection
Large Language Models Are Active Critics in NLG Evaluation
Shuying Xu, Junjie Hu, Ming Jiang
Large Language Model Language Generation Natural Language Generation Multiple Critic
Beyond Right and Wrong: Mitigating Cold Start in Knowledge Tracing Using Large Language Model and Option Weight
JongWoo Kim, SeongYeub Chu, Bryan Wong, Mun Yi
Large Language Model Knowledge Tracing Educational Data Cold Start Dynamic Weight
Large Language Model Evaluation via Matrix Nuclear-Norm
Yahan Li, Tingyu Xia, Yi Chang, Yuan Wu
Large Language Model Efficient Evaluation Nuclear Norm Dataset Compression Matrix Based Entropy
Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers
Aivin V. Solatorio, Gabriel Stefanini Vicente, Holly Krambeck, Olivier Dupriez
Large Language Model Artificial Intelligence Low Resource Language Non Native Climate Change Impact
Federated Data-Efficient Instruction Tuning for Large Language Models
Zhen Qin, Zhaomin Wu, Bingsheng He, Shuiguang Deng
Large Language Model Instruction Tuning Instruction Data Federated Instruction Tuning
Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation
Sharif Kazemi, Gloria Gerhardt, Jonty Katz, Caroline Ida Kuria, Estelle Pan, Umang Prabhakar
Large Language Model Training Data Low Resource Language Model Performance Language Pair Multilingual LLM Language Dataset Language Resource
Model-Based Differentially Private Knowledge Transfer for Large Language Models
Zhaomin Wu, Jizhou Guo, Junyi Hou, Bingsheng He, Lixin Fan, Qiang Yang
Large Language Model Full Model Domain Knowledge Large Language Domain Specific Task Domain Specific Model
TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs
Haochuan Wang, Xiachong Feng, Lei Li, Zhanyue Qin, Dianbo Sui, Lingpeng Kong
Large Language Model Critique Ability Strategy Logic Game Theory Data Leakage Strategic Ability
Skill Learning Using Process Mining for Large Language Model Plan Generation
Andrei Cosmin Redis, Mohammadreza Fani Sani, Bahram Zarrin, Andrea Burattin
Large Language Model Faithful Generation Skill Learning Skill Extraction
On Calibration of LLM-based Guard Models for Reliable Content Moderation
Hongfu Liu, Hengguan Huang, Hao Wang, Xiangming Gu, Ye Wang
Large Language Model Calibration Performance Content Moderation Confidence Calibration Air Guardian System
A Unified Approach to Routing and Cascading for LLMs
Jasper Dekoninck, Maximilian Baader, Martin Vechev
Large Language Model Unified Framework Model Selection Fine Tuned Model Dynamic Routing Routing Problem Cascade Model

Large Language Model

Papers

Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning

Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Focused ReAct: Improving ReAct through Reiterate and Early Stop

AFlow: Automating Agentic Workflow Generation

SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs

Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection

Large Language Models Are Active Critics in NLG Evaluation

Beyond Right and Wrong: Mitigating Cold Start in Knowledge Tracing Using Large Language Model and Option Weight

Large Language Model Evaluation via Matrix Nuclear-Norm

Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers

Federated Data-Efficient Instruction Tuning for Large Language Models

Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation

Model-Based Differentially Private Knowledge Transfer for Large Language Models

TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs

Skill Learning Using Process Mining for Large Language Model Plan Generation

On Calibration of LLM-based Guard Models for Reliable Content Moderation

A Unified Approach to Routing and Cascading for LLMs