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 10, 2024

Rewriting Conversational Utterances with Instructed Large Language Models
Elnara Galimzhanova, Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Guido Rocchietti
Large Language Model Conversational Context Shot Prompting Conversational Search
Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation
Sweta Agrawal, José G. C. de Souza, Ricardo Rei, António Farinhas, Gonçalo Faria, Patrick Fernandes, Nuno M Guerreiro, Andre Martins
Large Language Model Machine Translation Sentence Level Automatic Metric Preference Datasets
GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps
Muhammad Umair Nasir, Steven James, Julian Togelius
Large Language Model Natural Language Performance Score Game Environment Planning Ability Large Knowledge Model 2 Dimensional Map
Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data
Can Wang, Dianbo Sui, Hongliang Sun, Hao Ding, Bolin Zhang, Zhiying Tu
Large Language Model Context Learning Plug and Play Supervised Baseline Labeled Data
Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond
Qi Wang, Jindong Li, Shiqi Wang, Qianli Xing, Runliang Niu, He Kong, Rui Li, Guodong Long, Yi Chang, Chengqi Zhang
Large Language Model Timely Survey Recommender System Recommendation System Next Generation
Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
Yiming Chen, Yuan Zhang, Liyuan Cao, Kun Yuan, Zaiwen Wen
Large Language Model Language Model Parameter Efficient Fine Tuning LLM Fine Tuning Zeroth Order Low Rank Structure Multitask Finetuning
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
Songshuo Lu, Hua Wang, Yutian Rong, Zhi Chen, Yaohua Tang
Large Language Model Retrieval Augmented Generation Chunk Wise
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li
Large Language Model Retrieval Augmented Generation Free Lunch Fairness Implication Robust Fairness
Detecting Training Data of Large Language Models via Expectation Maximization
Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, Miguel Ballesteros, William Yang Wang
Large Language Model Membership Inference Attack Expectation Maximization Robust Method Pre Training Data Detection
KRAG Framework for Enhancing LLMs in the Legal Domain
Nguyen Ha Thanh, Ken Satoh
Large Language Model Language Model Retrieval Augmented Generation Language Understanding
OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting
Xukai Liu, Ye Liu, Kai Zhang, Kehang Wang, Qi Liu, Enhong Chen
Large Language Model Entity Mention Entity Linking Consensus Representation
MKGL: Mastery of a Three-Word Language
Lingbing Guo, Zhongpu Bo, Zhuo Chen, Yichi Zhang, Jiaoyan Chen, Yarong Lan, Mengshu Sun, Zhiqiang Zhang, Yangyifei Luo, Qian Li, Qiang Zhang, Wen Zhang, Huajun Chen
Large Language Model Natural Language Processing Knowledge Graph Expert Knowledge
Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)
Abhijit Mishra, Shreya Shukla, Jose Torres, Jacek Gwizdka, Shounak Roychowdhury
Large Language Model Text Generation EEG Data Thought Reasoning Brain Signal EEG Signal EEG Representation
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
Wenyuan Liu, Xindian Ma, Peng Zhang, Yan Wang
Large Language Model Post Training Quantization
Using LLMs to Discover Legal Factors
Morgan Gray, Jaromir Savelka, Wesley Oliver, Kevin Ashley
Large Language Model Structured Representation Legal Document Legal Reasoning Expert Advice Problem

October 9, 2024

MoDEM: Mixture of Domain Expert Models
Toby Simonds, Kemal Kurniawan, Jey Han Lau
Large Language Model Mixture Component Expert Model Domain Specific Model
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Siyu Zhou, Tianyi Zhou, Yijun Yang, Guodong Long, Deheng Ye, Jing Jiang, Chengqi Zhang
Large Language Model World Event World Model LLM Based Agent Agent Trajectory Rule Learning Model Based Agent
QuAILoRA: Quantization-Aware Initialization for LoRA
Neal Lawton, Aishwarya Padmakumar, Judith Gaspers, Jack FitzGerald, Anoop Kumar, Greg Ver Steeg, Aram Galstyan
Large Language Model Quantization Error Safe LoRA Accurate Quantization Driven Initialization
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan Ö. Arık
Large Language Model Retrieval Augmented Generation Retrieval Augmentation Knowledge Conflict
Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu
Large Language Model Unlearning Framework Preference Optimization Harmful Unlearning

Large Language Model

Papers

Rewriting Conversational Utterances with Instructed Large Language Models

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation

GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps

Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data

Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

Detecting Training Data of Large Language Models via Expectation Maximization

KRAG Framework for Enhancing LLMs in the Legal Domain

OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting

MKGL: Mastery of a Three-Word Language

Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs)

CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression

Using LLMs to Discover Legal Factors

MoDEM: Mixture of Domain Expert Models

WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents

QuAILoRA: Quantization-Aware Initialization for LoRA

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning