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 19, 2024

FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists
Tenghao Huang, Donghee Lee, John Sweeney, Jiatong Shi, Emily Steliotes, Matthew Lange, Jonathan May, Muhao Chen
Large Language Model Flavor Neutrino Physic
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
Eduardo Pignatelli, Johan Ferret, Tim Rockäschel, Edward Grefenstette, Davide Paglieri, Samuel Coward, Laura Toni
Large Language Model Language Model Reinforcement Learning Zero Shot Reward Shaping Reward Signal Temporal Credit Assignment
Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Parameter Optimization
Thomas Savage, Stephen Ma, Abdessalem Boukil, Vishwesh Patel, Ekanath Rangan, Ivan Rodriguez, Jonathan H Chen
Large Language Model Fine Tuning Integral Role Clinical Reasoning
Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models
Peiyi Zhang, Yazhou Zhang, Bo Wang, Lu Rong, Jing Qin
Large Language Model Automatic Evaluation Policy Value Chinese Benchmark
LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research
Yi Yang, Hanyu Duan, Jiaxin Liu, Kar Yan Tam
Large Language Model Strong Consistency LLM Based Evaluation Social Science Concurrent Validity Reproducible Evaluation Concept Vector Concept Trustworthiness
Exploring Large Language Models for Product Attribute Value Identification
Kassem Sabeh, Mouna Kacimi, Johann Gamper, Robert Litschko, Barbara Plank
Large Language Model Pre Trained Language Model Task Specific Instruction Fine Tuning Attribute Value Identification
Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
Aditya Joshi, Diptesh Kanojia, Heather Lent, Hour Kaing, Haiyue Song
Large Language Model Natural Language Processing Low Resource Language Multi Scenario Human Generated Idea Wide Variety Creole Language
Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories
Hikaru Asano, Ryo Yonetani, Taiki Sekii, Hiroki Ouchi
Large Language Model New Framework Image Captioning Generated Caption Captioning Model BERTScore Metric Motion Trajectory
Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni, Kelvin Xu, Sanil Jain, Rakesh Shivanna, Jeffrey Hui, Nishanth Dikkala, Mehran Kazemi, Bahare Fatemi, Rohan Anil, Ethan Dyer, Siamak Shakeri, Roopali Vij, Harsh Mehta, Vinay Ramasesh, Quoc Le, Ed Chi, Yifeng Lu, Orhan Firat, Angeliki Lazaridou, Jean-Baptiste Lespiau, Nithya Attaluri, Kate Olszewska
Large Language Model Long Context Latent Structure Long Context Language Long Context Understanding Video Haystack
Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillation
Graison Jos Thomas
Large Language Model BERT Model Financial Sentiment Analysis TinyBERT Model
Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning
Santosh Kumar Radha, Yasamin Nouri Jelyani, Ara Ghukasyan, Oktay Goktas
Large Language Model Complex Reasoning Task Thought Reasoning Problem Solving Dialog Agent
Enhancing SLM via ChatGPT and Dataset Augmentation
Tom Pieper, Mohamad Ballout, Ulf Krumnack, Gunther Heidemann, Kai-Uwe Kühnberger
Large Language Model Language Model ChatGPT Generated Conversation Natural Language Inference Smaller Language Model Dataset Augmentation
Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights
Mohamad Ballout, Ulf Krumnack, Gunther Heidemann, Kai-Uwe Kühnberger
Large Language Model Language Model Knowledge Distillation Task Specific Teacher Model
LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks
Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger
Large Language Model Hallucination Detection Waymo Open Motion Dataset
Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment
Tianyu Peng, Jiajun Zhang
Large Language Model Knowledge Distillation Multi Modal
Scaling FP8 training to trillion-token LLMs
Maxim Fishman, Brian Chmiel, Ron Banner, Daniel Soudry
Large Language Model Weight Re Mapping Synthetic Outlier Floating Point Quantization Int8 Training
LLMR: Knowledge Distillation with a Large Language Model-Induced Reward
Dongheng Li, Yongchang Hao, Lili Mou
Large Language Model Natural Language Processing Knowledge Distillation Large Language Dialogue Generation Augmented Language Model
CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs
Junlin Lv, Yuan Feng, Xike Xie, Xin Jia, Qirong Peng, Guiming Xie
Large Language Model Medical LLM Constructive Approach Well Defined Segment Long Context Task Criticality Analysis
Familiarity-aware Evidence Compression for Retrieval Augmented Generation
Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen
Large Language Model Retrieval Augmented Generation Evidence Retrieval
CodePlan: Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
Jiaxin Wen, Jian Guan, Hongning Wang, Wei Wu, Minlie Huang
Large Language Model Multi Step Reasoning Complex Reasoning Task Impressive Reasoning Capability Multi Step Reasoning Benchmark

Large Language Model

Papers

FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists

Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL

Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Parameter Optimization

Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models

LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research

Exploring Large Language Models for Product Attribute Value Identification

Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios

Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories

Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries

Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillation

Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning

Enhancing SLM via ChatGPT and Dataset Augmentation

Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights

LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks

Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment

Scaling FP8 training to trillion-token LLMs

LLMR: Knowledge Distillation with a Large Language Model-Induced Reward

CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs

Familiarity-aware Evidence Compression for Retrieval Augmented Generation

CodePlan: Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning