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 18, 2024

Mixture of Diverse Size Experts
Manxi Sun, Wei Liu, Jian Luan, Pengzhi Gao, Bin Wang
Large Language Model Mixture Component Token Generation Expert Selection Sparsely Activated Mixture of Expert
Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources
Issey Sukeda
Large Language Model Development Activity Multilingual Evaluation Cross Lingual Knowledge Transfer English Centric Low Computational Medical Question Answering Benchmark
Enabling Real-Time Conversations with Minimal Training Costs
Wang Xu, Shuo Wang, Weilin Zhao, Xu Han, Yukun Yan, Yudi Zhang, Zhe Tao, Zhiyuan Liu, Wanxiang Che
Large Language Model Real Time LLM Based Conversational Interaction Parallel Decoding Flexible Duplex
Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation
Chunliang Tao, Xiaojing Fan, Yahe Yang
Large Language Model Natural Language Processing Classification Code New Framework Synthetic Data Generation API Usage Natural Language Input Natural Language Command Dataset Creation
RUIE: Retrieval-based Unified Information Extraction using Large Language Model
Xincheng Liao, Junwen Duan, Yixi Huang, Jianxin Wang
Large Language Model Knowledge Distillation Information Extraction Information Extraction Task
Reward-Robust RLHF in LLMs
Yuzi Yan, Xingzhou Lou, Jialian Li, Yiping Zhang, Jian Xie, Chao Yu, Yu Wang, Dong Yan, Yuan Shen
Large Language Model Reward Model Reinforcement Learning From Human Feedback
Combating Phone Scams with LLM-based Detection: Where Do We Stand?
Zitong Shen, Kangzhong Wang, Youqian Zhang, Grace Ngai, Eugene Y. Fu
Large Language Model LLM Detector Conversational Dynamic
"A Woman is More Culturally Knowledgeable than A Man?": The Effect of Personas on Cultural Norm Interpretation in LLMs
Mahammed Kamruzzaman, Hieu Nguyen, Nazmul Hassan, Gene Louis Kim
Large Language Model Mixed Effect Personality Trait Social Norm Diverse Persona Persona Information

September 17, 2024

REAL: Response Embedding-based Alignment for LLMs
Honggen Zhang, Xufeng Zhao, Igor Molybog, June Zhang
Large Language Model Representation Alignment Dialogue Scenario Response Pair Redundancy Classifier
ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering
Priyesh Vakharia, Abigail Kufeldt, Max Meyers, Ian Lane, Leilani Gilpin
Large Language Model Interpretable Representation Neurosymbolic Approach Domain Specific Question Answering
PLATO: Planning with LLMs and Affordances for Tool Manipulation
Arvind Car, Sai Sravan Yarlagadda, Alison Bartsch, Abraham George, Amir Barati Farimani
Large Language Model Medical LLM Non Humanoid Robot Real World Task Planning Affordance Learning Autonomous Robot Robotic Platform Tool Manipulation
Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs
Guillermo Marco, Luz Rello, Julio Gonzalo
Large Language Model Language Model Textual Feature Short Text Human Written Text Creative Writing Creative Task Human Writer
Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement
Simon Yu, Liangyu Chen, Sara Ahmadian, Marzieh Fadaee
Large Language Model Fine Tuning Instruction Following Iterative Refinement Instruction Dataset Data Diversity Expert Diversification Training Iteration
CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration
Jiahui Gao, Renjie Pi, Tianyang Han, Han Wu, Lanqing Hong, Lingpeng Kong, Xin Jiang, Zhenguo Li
Large Language Model Multimodal Large Language Model Multimodal Control
P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task
Weiye Xu, Min Wang, Wengang Zhou, Houqiang Li
Large Language Model Retrieval Augmented Generation Task Planning Natural Language Instruction Task Specific Knowledge Embodied Task
LOLA -- An Open-Source Massively Multilingual Large Language Model
Nikit Srivastava, Denis Kuchelev, Tatiana Moteu, Kshitij Shetty, Michael Roeder, Diego Moussallem, Hamada Zahera, Axel-Cyrille Ngonga Ngomo
Large Language Model Language Generation Multilingual Large Language Model
LLM-as-a-Judge & Reward Model: What They Can and Cannot Do
Guijin Son, Hyunwoo Ko, Hoyoung Lee, Yewon Kim, Seunghyeok Hong
Large Language Model Long Form Answer Meta Evaluation
Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models
Bishwash Khanal, Jeffery M. Capone
Large Language Model Global Impact Model Compression Compression Technique Task Performance LLM Compression
Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Jianing Wang, Yang Zhou, Xiaocheng Zhang, Mengjiao Bao, Peng Yan
Large Language Model Preference Optimization Noisy Preference
Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning
Yukang Lin, Bingchen Zhong, Shuoran Jiang, Joanna Siebert, Qingcai Chen
Large Language Model Context Learning Semantic Similarity Exemplar Selection

Large Language Model

Papers

Mixture of Diverse Size Experts

Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources

Enabling Real-Time Conversations with Minimal Training Costs

Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation

RUIE: Retrieval-based Unified Information Extraction using Large Language Model

Reward-Robust RLHF in LLMs

Combating Phone Scams with LLM-based Detection: Where Do We Stand?

"A Woman is More Culturally Knowledgeable than A Man?": The Effect of Personas on Cultural Norm Interpretation in LLMs

REAL: Response Embedding-based Alignment for LLMs

ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering

PLATO: Planning with LLMs and Affordances for Tool Manipulation

Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs

Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement

CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration

P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task

LOLA -- An Open-Source Massively Multilingual Large Language Model

LLM-as-a-Judge & Reward Model: What They Can and Cannot Do

Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models

Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization

Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning