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 30, 2024

Resource Allocation for Stable LLM Training in Mobile Edge Computing
Chang Liu, Jun Zhao
Large Language Model Parameter Efficient Fine Tuning Resource Allocation Edge Computing Efficient Training Mobile Edge Computing LLM Training Edge Server
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Luohe Shi, Yao Yao, Zuchao Li, Lefei Zhang, Hai Zhao
Large Language Model Context Learning Retrieval Augmented Generation Inference Cost
Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language
Vincent Beliveau, Helene Kaas, Martin Prener, Claes N. Ladefoged, Desmond Elliott, Gitte M. Knudsen, Lars H. Pinborg, Melanie Ganz
Large Language Model Natural Language Processing Classification Code Natural Language Processing Model BERT Based Imbalanced Datasets Radiology Imaging Small Scale Multiple Language
Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback
Menna Fateen, Bo Wang, Tsunenori Mine
Large Language Model Language Model Human Feedback System Description Performance Score Modular System Prompt Generation Explanatory Feedback Short Answer
Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee
Large Language Model Raw Data Speech Analysis Pre Trained Speech Model LLM Generated Text
Do Influence Functions Work on Large Language Models?
Zhe Li, Wei Zhao, Yige Li, Jun Sun
Large Language Model Machine Learning Model Influence Function Hard Sample LLM Behavior
FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, Shafiq Joty
Large Language Model Language Model Context Information Comprehensive Benchmark
Enhancing High-order Interaction Awareness in LLM-based Recommender Model
Xinfeng Wang, Jin Cui, Fumiyo Fukumoto, Yoshimi Suzuki
Large Language Model Sequential Recommendation Recommendation Task LLM Based Recommender System Interaction Understanding
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Shuhao Chen, Weisen Jiang, Baijiong Lin, James T. Kwok, Yu Zhang
Large Language Model Contrastive Loss LLM Embeddings Dual Contrastive Learning Query Based
Neurosymbolic AI approach to Attribution in Large Language Models
Deepa Tilwani, Revathy Venkataramanan, Amit P. Sheth
Large Language Model Attribution Method External Knowledge Source Attribution Neurosymbolic AI Unreliable Source

September 29, 2024

Calibrating Language Models with Adaptive Temperature Scaling
Johnathan Xie, Annie S. Chen, Yoonho Lee, Eric Mitchell, Chelsea Finn
Large Language Model Supervised Fine Tuning Temperature Scaling Natural Language Processing Benchmark
Transforming Hidden States into Binary Semantic Features
Tomáš Musil, David Mareček
Large Language Model Semantic Feature Hidden State NLP Application Distributional Semantics Binary Feature Distributional Approach
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
Yung-Chieh Chan, George Pu, Apaar Shanker, Parth Suresh, Penn Jenks, John Heyer, Sam Denton
Large Language Model Synthetic Data Generation Data Generation Knowledge Augmentation Balancing Market
AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
Rui Pan, Tuan Dung Nguyen, Hardik Arora, Alberto Accomazzi, Tirthankar Ghosal, Yuan-Sen Ting
Large Language Model Full Model Astronomical Data Continual Pre Training LLM Benchmark
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead
Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, Yongbo Wang, Feng Wang, Jingtong Wu, Xin Lu, Rui Yan
Large Language Model Retrieval Augmented Generation Attention Weight Context Awareness Position Embeddings
2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
Jia-Nan Li, Jian Guan, Wei Wu, Zhengtao Yu, Rui Yan
Large Language Model Positional Encoding Structured Information Table Understanding
Learning Attentional Mixture of LoRAs for Language Model Continual Learning
Jialin Liu, Jianhua Wu, Jie Liu, Yutai Duan
Large Language Model Language Model Continual LEArning Continual Learning Continual Learning Benchmark Run LoRA Run Mixture of Attention
Hyper-Connections
Defa Zhu, Hongzhi Huang, Zihao Huang, Yutao Zeng, Yunyao Mao, Banggu Wu, Qiyang Min, Xun Zhou
Large Language Model Residual Connection Representation Collapse Hyper Network
LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
Shaolin Zhu, Leiyu Pan, Bo Li, Deyi Xiong
Large Language Model Machine Translation Language Pair Multilingual Translation Translation Datasets Cross Lingual Supervision
MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
Vibhor Agarwal, Yiqiao Jin, Mohit Chandra, Munmun De Choudhury, Srijan Kumar, Nishanth Sastry
Large Language Model Hallucination Detection Non Negative Textual Response LLM Response Visual Hallucination LLM Hallucination

Large Language Model

Papers

Resource Allocation for Stable LLM Training in Mobile Edge Computing

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Classification of Radiological Text in Small and Imbalanced Datasets in a Non-English Language

Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback

Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data

Do Influence Functions Work on Large Language Models?

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"

Enhancing High-order Interaction Awareness in LLM-based Recommender Model

RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models

Neurosymbolic AI approach to Attribution in Large Language Models

Calibrating Language Models with Adaptive Temperature Scaling

Transforming Hidden States into Binary Semantic Features

Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs

AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy

PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead

2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models

Learning Attentional Mixture of LoRAs for Language Model Continual Learning

Hyper-Connections

LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation

MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models