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

January 3, 2025

A non-ergodic framework for understanding emergent capabilities in Large Language Models
Javier Marin
Large Language Model Language Model Path Breaking Emergence Emergent Ability Non Ergodic

January 2, 2025

Predicting the Performance of Black-box LLMs through Self-Queries
Dylan Sam, Marc Finzi, J. Zico Kolter
Large Language Model Language Model System Performance Adversarial Prompt Question Answering Task Model Generalizability Black Box Large Language Model
Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information
Rasul Tutnov, Antoine Grosnit, Haitham Bou-Ammar
Large Language Model Mutual Information Alignment Problem Anti Unification
Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension
Yanbo Fang, Ruixiang Tang
Large Language Model New Framework Knowledge Comprehension Capability Low Confidence Model Understanding Encoded Knowledge
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen
Large Language Model Text Generation Text Generation Model Dual Process
Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case
Kaushik Roy, Harshul Surana, Darssan Eswaramoorthi, Yuxin Zi, Vedant Palit, Ritvik Garimella, Amit Sheth
Large Language Model Anxiety Disorder Mental Health Assessment
Does a Large Language Model Really Speak in Human-Like Language?
Mose Park, Yunjin Choi, Jong-June Jeon
Large Language Model Text Generation Human Like LLM Generated
Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?
Manuel Weber, Moritz Huber, Maximilian Auch, Alexander Döschl, Max-Emanuel Keller, Peter Mandl
Large Language Model Hate Speech Online Comment Toxic Comment Perspective View
Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion
Qiyuan He, Jianfei Yu, Wenya Wang
Large Language Model Knowledge Base Large Language Symbolic Reasoning Rule Based Knowledge Base Completion
Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search
Shuangtao Li, Shuaihao Dong, Kexin Luan, Xinhan Di, Chaofan Ding
Large Language Model Complex Reasoning Search Query Reasoning Datasets Reasoning Step Process Supervision
Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design Projects
Abdullah Mushtaq, Muhammad Rafay Naeem, Ibrahim Ghaznavi, Muhammad Imran Taj, Imran Hashmi, Junaid Qadir
Large Language Model New Framework Collective Intelligence Wire Harness Interdisciplinary Research Swarm Learning
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
Yanwen Huang, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao
Large Language Model Context Information Context Attention Contextual Integrity Context Utilization
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Xinshuo Hu, Zifei Shan, Xinping Zhao, Zetian Sun, Zhenyu Liu, Dongfang Li, Shaolin Ye, Xinyuan Wei, Qian Chen, Baotian Hu, Haofen Wang, Jun Yu, Min Zhang
Large Language Model Training Data
MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model
Chengze Zhang, Changshan Li, Shiyang Gao
Large Language Model Game Narrative Insight Generation Data Storytelling

January 1, 2025

Aligning LLMs with Domain Invariant Reward Models
David Wu, Sanjiban Choudhury
Large Language Model Cross Lingual Transfer Reward Model Large Language Model Alignment Domain Loss
Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things
Talha Zeeshan, Abhishek Kumar, Susanna Pirttikangas, Sasu Tarkoma
Large Language Model Multi Agent Framework LLM Based Framework Data Analysis Pipeline Event Processing
Representation in large language models
Cameron C. Yetman
Large Language Model Language Model Meaningful Representation Individual Representation Recent Large Language Model Representation Model Quantum Cognition
TrustRAG: Enhancing Robustness and Trustworthiness in RAG
Huichi Zhou, Kin-Hei Lee, Zhonghao Zhan, Yue Chen, Zhenhao Li
Large Language Model Native Robustness Retrieval Augmented Generation Data Poisoning Attack
LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models
Hieu Man, Nghia Trung Ngo, Viet Dac Lai, Ryan A. Rossi, Franck Dernoncourt, Thien Huu Nguyen
Large Language Model Jina Embeddings Multilingual Encoders Language Space Cross Lingual Performance Cross Lingual Supervision Task Specific Embeddings
NMM-HRI: Natural Multi-modal Human-Robot Interaction with Voice and Deictic Posture via Large Language Model
Yuzhi Lai, Shenghai Yuan, Youssef Nassar, Mingyu Fan, Atmaraaj Gopal, Arihiro Yorita, Naoyuki Kubota, Matthias Rätsch
Large Language Model Human Robot Interaction Multimodal Interaction Natural Language Command Universal Robot

Large Language Model

Papers

A non-ergodic framework for understanding emergent capabilities in Large Language Models

Predicting the Performance of Black-box LLMs through Self-Queries

Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information

Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking

Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case

Does a Large Language Model Really Speak in Human-Like Language?

Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?

Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion

Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search

Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design Projects

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model

MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model

Aligning LLMs with Domain Invariant Reward Models

Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things

Representation in large language models

TrustRAG: Enhancing Robustness and Trustworthiness in RAG

LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models

NMM-HRI: Natural Multi-modal Human-Robot Interaction with Voice and Deictic Posture via Large Language Model