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 11, 2024

SimulBench: Evaluating Language Models with Creative Simulation Tasks
Qi Jia, Xiang Yue, Tianyu Zheng, Jie Huang, Bill Yuchen Lin
Large Language Model Language Model Simulation Study Multi Turn Dialogue Simulation Environment Creative Task
When Less Is Not More: Large Language Models Normalize Less-Frequent Terms with Lower Accuracy
Daniel B. Hier, Thanh Son Do, Tayo Obafemi-Ajayi
Large Language Model Language Model Low Precision Text Normalization Phenotypic Data
Contextualization of ASR with LLM using phonetic retrieval-based augmentation
Zhihong Lei, Xingyu Na, Mingbin Xu, Ernest Pusateri, Christophe Van Gysel, Yuanyuan Zhang, Shiyi Han, Zhen Huang
Large Language Model Automatic Speech Recognition Medical LLM Speech Recognition Word Error Rate Error Mitigation LLM in Context
AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
Large Language Model Contrastive Learning Parametric Knowledge Knowledge Conflict
Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation
SeongYeub Chu, JongWoo Kim, MunYong Yi
Large Language Model Real Human Text Evaluation Digital Action
MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications
Praveen K Kanithi, Clément Christophe, Marco AF Pimentel, Tathagata Raha, Nada Saadi, Hamza Javed, Svetlana Maslenkova, Nasir Hayat, Ronnie Rajan, Shadab Khan
Large Language Model Medical Question Answering Medical Dialogue Healthcare Application Medical Reasoning Clinical Application Multi Dimensional Evaluation
Alignment of Diffusion Models: Fundamentals, Challenges, and Future
Buhua Liu, Shitong Shao, Bao Li, Lichen Bai, Haoyi Xiong, James Kwok, Sumi Helal, Zeke Xie
Large Language Model Diffusion Model Technical Challenge Generative Modeling Alignment Problem Future Reasoning Basic Concept Alignment Approach Preference Based
LLM-based feature generation from text for interpretable machine learning
Vojtěch Balek, Lukáš Sýkora, Vilém Sklenák, Tomáš Kliegr
Large Language Model Text Modality Text Classification Text Representation Interpretable Machine Learning Interpretable Feature Feature Generation
Reranking Laws for Language Generation: A Communication-Theoretic Perspective
António Farinhas, Haau-Sing Li, André F. T. Martins
Large Language Model Machine Translation Code Generation Language Generation Ranking Model Noisy Channel Noisy Communication Communication Perspective
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Qianli Wang, Tatiana Anikina, Nils Feldhus, Simon Ostermann, Sebastian Möller, Vera Schmitt
Large Language Model LeArning Abstract Natural Language Explanation Explanation Generation Self Refinement Explanation Selection
Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
Daehee Kim, Deokhyung Kang, Sangwon Ryu, Gary Geunbae Lee
Large Language Model Knowledge Graph to Text Textual Graph
Understanding Knowledge Drift in LLMs through Misinformation
Alina Fastowski, Gjergji Kasneci
Large Language Model Misinformation Claim Adversarial Input Token Prediction
Native vs Non-Native Language Prompting: A Comparative Analysis
Mohamed Bayan Kmainasi, Rakif Khan, Ali Ezzat Shahroor, Boushra Bendou, Maram Hasanain, Firoj Alam
Large Language Model Natural Language Processing Comparative Study Natural Language Instruction Native Speaker
Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency
Hanyu Zhao, Li Du, Yiming Ju, Chengwei Wu, Tengfei Pan
Large Language Model Visual Perspective Curriculum Learning Instruction Generation Instruction Datasets Design Pattern Dependency Aware Incident Instruction Paradigm Search Augmented Instruction Learning
Representation Tuning
Christopher M. Ackerman
Large Language Model Token Prediction Residual Stream Representation Finetuning Activation Vector
A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models
Daniel B. Hier, Thanh Son Do, Tayo Obafemi-Ajayi
Large Language Model Retriever Reader Feature Normalization Entity Normalization Phenotype Recognition Continuous Valued Phenotype
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
Lijia Lv, Weigang Zhang, Xuehai Tang, Jie Wen, Feng Liu, Jizhong Han, Songlin Hu
Large Language Model Jailbreak Attack

September 10, 2024

Semi-Supervised Reward Modeling via Iterative Self-Training
Yifei He, Haoxiang Wang, Ziyan Jiang, Alexandros Papangelis, Han Zhao
Large Language Model Self Training Reward Model Semi Supervised Reward
MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders
Wenyu Zhang, Shuo Sun, Bin Wang, Xunlong Zou, Zhuohan Liu, Yingxu He, Geyu Lin, Nancy F. Chen, Ai Ti Aw
Large Language Model Pre Trained Mixture Component Lightweight Encoder
Beyond designer's knowledge: Generating materials design hypotheses via large language models
Quanliang Liu, Maciej P. Polak, So Yeon Kim, MD Al Amin Shuvo, Hrishikesh Shridhar Deodhar, Jeongsoo Han, Dane Morgan, Hyunseok Oh
Large Language Model Knowledge Based Material Discovery Material Design Artifact Design High Entropy Alloy Ion Transport

Large Language Model

Papers

SimulBench: Evaluating Language Models with Creative Simulation Tasks

When Less Is Not More: Large Language Models Normalize Less-Frequent Terms with Lower Accuracy

Contextualization of ASR with LLM using phonetic retrieval-based augmentation

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge

Think Together and Work Better: Combining Humans' and LLMs' Think-Aloud Outcomes for Effective Text Evaluation

MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications

Alignment of Diffusion Models: Fundamentals, Challenges, and Future

LLM-based feature generation from text for interpretable machine learning

Reranking Laws for Language Generation: A Communication-Theoretic Perspective

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem

Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model

Understanding Knowledge Drift in LLMs through Misinformation

Native vs Non-Native Language Prompting: A Comparative Analysis

Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency

Representation Tuning

A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs

Semi-Supervised Reward Modeling via Iterative Self-Training

MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders

Beyond designer's knowledge: Generating materials design hypotheses via large language models