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

September 13, 2024

KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models
Neel Rajani, Lilli Kiessling, Aleksandr Ogaltsov, Claus Lang
Large Language Model Model Evaluation State of the Art LLM Single Parent Family Financial Large Language Model FINancial Task Instruct Model
Your Weak LLM is Secretly a Strong Teacher for Alignment
Leitian Tao, Yixuan Li
Large Language Model Alignment Problem Good Teacher Lightweight LLM
L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context
Pritika Rohera, Chaitrali Ginimav, Akanksha Salunke, Gayatri Sawant, Raviraj Joshi
Large Language Model Data Set Multilingual Model Indian Language Multilingual Large Language Model Challenging Benchmark L3Cube MahaSocialNER Indian English
Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions
Lingwei Meng, Shujie Hu, Jiawen Kang, Zhaoqing Li, Yuejiao Wang, Wenxuan Wu, Xixin Wu, Xunying Liu, Helen Meng
Large Language Model Automatic Speech Recognition Speech Analysis Multi Speaker Diverse Instruction Multi Talker Environment
Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia
Fajri Koto
Large Language Model Real World Code Multiple Choice Question Job Market Local Context Credential Related Term
Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding
Tianqiao Liu, Zui Chen, Zitao Liu, Mi Tian, Weiqi Luo
Large Language Model Chain of Thought Hidden Knowledge Compressed Representation Semantic Compression
LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study
Mahta Fetrat Qharabagh, Zahra Dehghanian, Hamid R. Rabiee
Large Language Model New Benchmark Case Study Speech Synthesis Speech Processing Grapheme to Phoneme
ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model
Zezheng Qin
Large Language Model Recommender System Adaptation Concern Recommendation Performance Music Recommendation Audio Visual Fusion Multimodal Recommender System
Eir: Thai Medical Large Language Models
Yutthakorn Thiprak, Rungtam Ngodngamthaweesuk, Songtam Ngodngamtaweesuk
Large Language Model Medical LLM Open Source Large Language Model
When Context Leads but Parametric Memory Follows in Large Language Models
Yufei Tao, Adam Hiatt, Erik Haake, Antonie J. Jetter, Ameeta Agrawal
Large Language Model Context Information Parametric Knowledge Context Size Non Parametric Memory

September 12, 2024

Knowledge Tagging with Large Language Model based Multi-Agent System
Hang Li, Tianlong Xu, Ethan Chang, Qingsong Wen
Large Language Model Multi Agent System Semantic Understanding Knowledge Tagging
An Experimental Study of Competitive Market Behavior Through LLMs
Jingru Jia, Zehua Yuan
Large Language Model Experimental Study Competition Dynamic Market Dynamic Market Simulation
Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue
Johnathan Ivey, Shivani Kumar, Jiayu Liu, Hua Shen, Sushrita Rakshit, Rohan Raju, Haotian Zhang, Aparna Ananthasubramaniam, Junghwan Kim, Bowen Yi, Dustin Wright, Abraham Israeli, Anders Giovanni Møller, Lechen Zhang, David Jurgens
Large Language Model Non Humanoid Robot Dialogue Utterance User Response Human Dialogue
Faster Speech-LLaMA Inference with Multi-token Prediction
Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
Large Language Model Scientific Inference Speech Encoder
LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Models
Zhengliang Liu, Yiwei Li, Oleksandra Zolotarevych, Rongwei Yang, Tianming Liu
Large Language Model New Framework Discourse Structure LLM Evaluation Debate Evaluation
ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement
Oishik Chatterjee, Pooja Aggarwal, Suranjana Samanta, Ting Dai, Prateeti Mohapatra, Debanjana Kar, Ruchi Mahindru, Steve Barbieri, Eugen Postea, Brad Blancett, Arthur De Magalhaes
Large Language Model Code Generation Direct Assessment LLM Based Framework Reliability Assessment Commitment
WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks
Jingwen Tong, Jiawei Shao, Qiong Wu, Wei Guo, Zijian Li, Zehong Lin, Jun Zhang
Large Language Model AI Agent Wireless Network AI Based Intelligent Network
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
Atilla Akkus, Mingjie Li, Junjie Chu, Michael Backes, Yang Zhang, Sinem Sav
Large Language Model Synthetic Data Membership Inference Attack Privacy Preserving LLM Generated Hidden Risk Privacy Breach
Full-text Error Correction for Chinese Speech Recognition with Large Language Model
Zhiyuan Tang, Dong Wang, Shen Huang, Shidong Shang
Large Language Model Automatic Speech Recognition Speech Recognition Speech Data Error Correction Error Correcting Code
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
Xun Xian, Ganghua Wang, Xuan Bi, Jayanth Srinivasa, Ashish Kundu, Charles Fleming, Mingyi Hong, Jie Ding
Large Language Model Adversarial Robustness Retrieval Augmented Generation Domain Knowledge Information Retrieval Latent Vulnerability Malicious Query

Large Language Model

Papers

KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models

Your Weak LLM is Secretly a Strong Teacher for Alignment

L3Cube-IndicQuest: A Benchmark Question Answering Dataset for Evaluating Knowledge of LLMs in Indic Context

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions

Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding

LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study

ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model

Eir: Thai Medical Large Language Models

When Context Leads but Parametric Memory Follows in Large Language Models

Knowledge Tagging with Large Language Model based Multi-Agent System

An Experimental Study of Competitive Market Behavior Through LLMs

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue

Faster Speech-LLaMA Inference with Multi-token Prediction

LLM-POTUS Score: A Framework of Analyzing Presidential Debates with Large Language Models

ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement

WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks

Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data

Full-text Error Correction for Chinese Speech Recognition with Large Language Model

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains