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 9, 2024

DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI
Hyowon Cho, Soonwon Ka, Daechul Park, Jaewook Kang, Minjoon Seo, Bokyung Son
Large Language Model Data Centric AI Researcher
Methods for Legal Citation Prediction in the Age of LLMs: An Australian Law Case Study
Ehsan Shareghi, Jiuzhou Han, Paul Burgess
Large Language Model NCD Method Speech Based Age Retrieval Augmentation Instruction Tuned Large Language Model Legal Case Retrieval Method
Blockchain Data Analysis in the Era of Large-Language Models
Kentaroh Toyoda, Xiao Wang, Mingzhe Li, Bo Gao, Yuan Wang, Qingsong Wei
Large Language Model New Era Smart Contract LLM Integrated Application Blockchain Transaction
Unseen Attack Detection in Software-Defined Networking Using a BERT-Based Large Language Model
Mohammed N. Swileh (1), Shengli Zhang (1) ((1) College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China)
Large Language Model Network Traffic Software Defined Attack Detection Decision Based
LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments
Prakash Aryan
Large Language Model Genetic Algorithm Adversarial Text Discourse Structure Debate Evaluation Computational Argumentation Counter Argument Diverse Argument
Enhancing Adversarial Resistance in LLMs with Recursion
Bryan Li, Sounak Bagchi, Zizhan Wang
Large Language Model Text Simplification Adversarial Prompt Recursive Algorithm Robust Defense Malicious Traffic
Hate Speech According to the Law: An Analysis for Effective Detection
Katerina Korre, John Pavlopoulos, Paolo Gajo, Alberto Barrón-Cedeño
Large Language Model General Analysis Hate Speech Legal Text Efficient Detection
AIDE: Task-Specific Fine Tuning with Attribute Guided Multi-Hop Data Expansion
Jiayu Li, Xuan Zhu, Fang Liu, Yanjun Qi
Large Language Model Training Data Task Specific Data Synthesis Prompt Expansion

December 8, 2024

Infusing Prompts with Syntax and Semantics
Anton Bulle Labate, Fabio Gagliardi Cozman
Large Language Model Language Model Complex Prompt Semantics Surfaced Semantic Information Code Syntax Linguistic Analysis
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
Fan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang
Large Language Model Language Understanding Parameter Efficient Fine Tuning Implicit Knowledge Singular Vector
Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features
Muhammad Imran, Abdul Wahab Ziaullah, Kai Chen, Ferda Ofli
Large Language Model Natural Language Social Medium Data Robustness Evaluation Linguistic Feature Task Performance
Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents
Zhiguang Wu, Fengbin Zhu, Xuequn Shang, Yupei Zhang, Pan Zhou
Large Language Model Text to SQL New Database Query Generation Refined Schema SQL Generation
Are Clinical T5 Models Better for Clinical Text?
Yahan Li, Keith Harrigian, Ayah Zirikly, Mark Dredze
Large Language Model Clinical Text T5 Model

December 7, 2024

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models
Haizhou Shi, Yibin Wang, Ligong Han, Huan Zhang, Hao Wang
Large Language Model Full Model Variational Inference Bayesian Inference Low Rank Large Language Training Free Adapter Module Reliable Uncertainty
Semantic loss guided data efficient supervised fine tuning for Safe Responses in LLMs
Yuxiao Lu, Arunesh Sinha, Pradeep Varakantham
Large Language Model Fine Tuning Non Negative Textual Response LLM Safety Toxic Comment Semantic Loss Contrastive Data
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds
Lei Wang, Jianxun Lian, Yi Huang, Yanqi Dai, Haoxuan Li, Xu Chen, Xing Xie, Ji-Rong Wen
Large Language Model Fine Grained Character Level Role Playing Virtual World
Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
Large Language Model LeArning Abstract Structured Representation Reason Giving Abstract Reasoning Neuro Symbolic Approach Vector Symbolic Architecture Visual Abstract Reasoning Arithmetic Circuit
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, Yiqun Liu
Large Language Model Comprehensive Survey LLM Based Evaluation Meta Evaluation
A polar coordinate system represents syntax in large language models
Pablo Diego-Simón, Stéphane D'Ascoli, Emmanuel Chemla, Yair Lakretz, Jean-Rémi King
Large Language Model Code Syntax Symbolic Representation Polar Representation Syntactic Graph Syntactic Relation
A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions
Ola Shorinwa, Zhiting Mei, Justin Lidard, Allen Z. Ren, Anirudha Majumdar
Large Language Model Uncertainty Quantification Chatbot Response Comprehensive Taxonomy Future Direction Commonsense Reasoning Research Challenge Non Factual

Large Language Model

Papers

DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI

Methods for Legal Citation Prediction in the Age of LLMs: An Australian Law Case Study

Blockchain Data Analysis in the Era of Large-Language Models

Unseen Attack Detection in Software-Defined Networking Using a BERT-Based Large Language Model

LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments

Enhancing Adversarial Resistance in LLMs with Recursion

Hate Speech According to the Law: An Analysis for Effective Detection

AIDE: Task-Specific Fine Tuning with Attribute Guided Multi-Hop Data Expansion

Infusing Prompts with Syntax and Semantics

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models

Evaluating Robustness of LLMs on Crisis-Related Microblogs across Events, Information Types, and Linguistic Features

Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents

Are Clinical T5 Models Better for Clinical Text?

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Semantic loss guided data efficient supervised fine tuning for Safe Responses in LLMs

CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds

Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning

LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

A polar coordinate system represents syntax in large language models

A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions