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 9, 2024

Mental Disorders Detection in the Era of Large Language Models
Gleb Kuzmin, Petr Strepetov, Maksim Stankevich, Ivan Smirnov, Artem Shelmanov
Large Language Model Language Model Mental Health New Era Encoder Based
Personalized Visual Instruction Tuning
Renjie Pi, Jianshu Zhang, Tianyang Han, Jipeng Zhang, Rui Pan, Tong Zhang
Large Language Model Multimodal Large Language Model Visual Instruction Tuning Coherent Dialogue
I Want to Break Free! Anti-Social Behavior and Persuasion Ability of LLMs in Multi-Agent Settings with Social Hierarchy
Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì, Marco Guerini, Bruno Lepri, Jacopo Staiano
Large Language Model Medical LLM Part Whole Hierarchy Multi Agent Setting interactiOn Pattern Persuasive Capability Antisocial Behavior
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Sangwon Yu, Ik-hwan Kim, Jongyoon Song, Saehyung Lee, Junsung Park, Sungroh Yoon
Large Language Model Multi Step Reasoning Multi Hop Reasoning Self Repetition Multi Hop QA
Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning
Zhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, Kaize Ding
Large Language Model Graph Neural Network Context Learning Graph Structured Data Text Attributed Graph Context Graph
Capturing Bias Diversity in LLMs
Purva Prasad Gosavi, Vaishnavi Murlidhar Kulkarni, Alan F. Smeaton
Large Language Model Potential Bias Inclusive Artificial Intelligence Diverse Perspective
Robots in the Middle: Evaluating LLMs in Dispute Resolution
Jinzhe Tan, Hannes Westermann, Nikhil Reddy Pottanigari, Jaromír Šavelka, Sébastien Meeùs, Mia Godet, Karim Benyekhlef
Large Language Model Non Humanoid Robot Customer Service Low Priority Observed Mediator
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
Zekun Wang, Feiyu Duan, Yibo Zhang, Wangchunshu Zhou, Ke Xu, Wenhao Huang, Jie Fu
Large Language Model Product Specific Position Information Copy Paste Length Constraint Data Copying Position Awareness Text Length
Parameter-Efficient Fine-Tuning via Selective Discrete Cosine Transform
Yixian Shen, Qi Bi, Jia-Hong Huang, Hongyi Zhu, Anuj Pathania
Large Language Model Parameter Efficient Fine Tuning Discrete Cosine Transform Trainable Parameter
CursorCore: Assist Programming through Aligning Anything
Hao Jiang, Qi Liu, Rui Li, Shengyu Ye, Shijin Wang
Large Language Model Code Completion Programming Task Better Alignment
Fine-tuning can Help Detect Pretraining Data from Large Language Models
Hengxiang Zhang, Songxin Zhang, Bingyi Jing, Hongxin Wei
Large Language Model Fine Tuning Data Detection Raw Data Unseen Data
Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, Fazl Barez
Large Language Model Latent Space Latent Representation Sparse Autoencoders Universal Feature
Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara
Azree Nazri, Olalekan Agbolade, Faisal Aziz
Large Language Model Language Model Intelligent Assistant Better Language Model Specific Model
Uncovering Factor Level Preferences to Improve Human-Model Alignment
Juhyun Oh, Eunsu Kim, Jiseon Kim, Wenda Xu, Inha Cha, William Yang Wang, Alice Oh
Large Language Model Preference Alignment Model Alignment
Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models
Daniel Albert, Stephan Billinger
Large Language Model Optical Experiment Cognitive Process Search Behavior
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, Wenjie Li
Large Language Model LLM Inference SWIFT DynGFN Draft Model
Generative Model for Less-Resourced Language with 1 billion parameters
Domen Vreš, Martin Božič, Aljaž Potočnik, Tomaž Martinčič, Marko Robnik-Šikonja
Large Language Model Generative Model Generative Modeling Many Parameter Sentence Simplification
FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding
Jingyang Deng, Zhengyang Shen, Boyang Wang, Lixin Su, Suqi Cheng, Ying Nie, Junfeng Wang, Dawei Yin, Jinwen Ma
Large Language Model Human Understanding Long Context Long Context Large Language Model Long Context LLM Long Context Understanding Context Propagation
Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level
Xinyi Zeng, Yuying Shang, Yutao Zhu, Jiawei Chen, Yu Tian
Large Language Model Medical LLM Human SAFETY Speculative Decoding Accurate Decoding Malicious Prompt
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Donghyun Lee, Mo Tiwari
Large Language Model Multi Agent System LLM Based Prompt Injection Attack Prompt Injection Malicious Prompt Infection Risk

Large Language Model

Papers

Mental Disorders Detection in the Era of Large Language Models

Personalized Visual Instruction Tuning

I Want to Break Free! Anti-Social Behavior and Persuasion Ability of LLMs in Multi-Agent Settings with Social Hierarchy

Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context

Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning

Capturing Bias Diversity in LLMs

Robots in the Middle: Evaluating LLMs in Dispute Resolution

PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness

Parameter-Efficient Fine-Tuning via Selective Discrete Cosine Transform

CursorCore: Assist Programming through Aligning Anything

Fine-tuning can Help Detect Pretraining Data from Large Language Models

Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models

Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara

Uncovering Factor Level Preferences to Improve Human-Model Alignment

Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models

SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Generative Model for Less-Resourced Language with 1 billion parameters

FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding

Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level

Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems