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

October 11, 2024

Using off-the-shelf LLMs to query enterprise data by progressively revealing ontologies
C. Civili, E. Sherkhonov, R.E.K. Stirewalt
Large Language Model Natural Language Raw Data Top Level Ontology SPARQL Query
Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
Yimin Tang, Yurong Xu, Ning Yan, Masood Mortazavi
Large Language Model Medical LLM Long Context Functional Mechanism Short Term Memory Retrieval Augmented LLM
P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan
Large Language Model Logical Reasoning Reasoning ChAin Logical Reasoning Capability Logical Reasoning Datasets Reasoning Chain
Can a large language model be a gaslighter?
Wei Li, Luyao Zhu, Yang Song, Ruixi Lin, Rui Mao, Yang You
Large Language Model Fine Tuning Serial Manipulator Two Stage Deep Learning
Enterprise Benchmarks for Large Language Model Evaluation
Bing Zhang, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Md. Maruf Hossain, Guang-Jie Ren, Kate Soule, Yada Zhu
Large Language Model Domain Specific NLP Task Diverse Domain
Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications
Alexey Zhezherau, Alexei Yanockin
Large Language Model Synthetic Data Medical LLM Domain Specific Model Performance Virtual Character Real Datasets Real World Interaction
SimpleStrat: Diversifying Language Model Generation with Stratification
Justin Wong, Yury Orlovskiy, Michael Luo, Sanjit A. Seshia, Joseph E. Gonzalez
Large Language Model Language Model Scientific Inference Synthetic Data Generation Language Model Generation Hierarchical Bias Driven Stratification Diverse Response
Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration
Cheng Qian, Xianglong Shi, Shanshan Yao, Yichen Liu, Fengming Zhou, Zishu Zhang, Junaid Akram, Ali Braytee, Ali Anaissi
Large Language Model Medical LLM BERT Model Service Provider BioASQ Challenge
The structure of the token space for large language models
Michael Robinson, Sourya Dey, Shauna Sweet
Large Language Model Latent Space Inner Structure
SubZero: Random Subspace Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning
Ziming Yu, Pan Zhou, Sike Wang, Jia Li, Hua Huang
Large Language Model Language Model LLM Fine Tuning Zeroth Order Gradient Backpropagation Random Subspace
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda, Daniel Khashabi, Benjamin Van Durme
Large Language Model Diverse Set Safety Alignment Model Safety Enhancing Safety Contextual Alignment
Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
Aymane El Firdoussi, Mohamed El Amine Seddik, Soufiane Hayou, Reda Alami, Ahmed Alzubaidi, Hakim Hacid
Large Language Model Synthetic Data Theoretical Understanding Full Potential Label Noise DCU Insight AQ Random Matrix Data Pruning
A Benchmark for Cross-Domain Argumentative Stance Classification on Social Media
Jiaqing Yuan, Ruijie Xi, Munindar P. Singh
Large Language Model New Benchmark Social Medium Human Annotation Manual Annotation
Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies
Yingqiang Gao, Lukas Fischer, Alexa Lintner, Sarah Ebling
Large Language Model Natural Language Processing Generative AI Narrative Review Vision Language Audio Description
Measuring the Inconsistency of Large Language Models in Preferential Ranking
Xiutian Zhao, Ke Wang, Wei Peng
Large Language Model Preference Feedback Partial Ranking Hard to Easy Inconsistency Preference Rating Order Model Strong Transitivity Relation
Do Unlearning Methods Remove Information from Language Model Weights?
Aghyad Deeb, Fabien Roger
Large Language Model Unlearning Framework New Attack Adversarial Evaluation
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Zhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin, Yaojie Lu, Qiaoyu Tang, Fei Huang, Xianpei Han, Le Sun, Yongbin Li
Large Language Model Retrieval Augmented Generation Structural Information Structured Knowledge
Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs
Chris Cummins, Volker Seeker, Jordi Armengol-Estapé, Aram H. Markosyan, Gabriel Synnaeve, Hugh Leather
Large Language Model Real World Code Rewrite System Code Transformation
Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models
Reza Abbasi, Sernam Lim
Large Language Model Vision Language Model Artificial Intelligence Model Large Model Based Model Large AI Model GPU Memory Stage Pipeline
Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
Yeeun Kim, Young Rok Choi, Eunkyung Choi, Jinhwan Choi, Hai Jin Park, Wonseok Hwang
Large Language Model Human Understanding Benchmark Study Legal Reasoning Legal Task State Medical Licensing Examination

Large Language Model

Papers

Using off-the-shelf LLMs to query enterprise data by progressively revealing ontologies

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains

Can a large language model be a gaslighter?

Enterprise Benchmarks for Large Language Model Evaluation

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications

SimpleStrat: Diversifying Language Model Generation with Stratification

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

The structure of the token space for large language models

SubZero: Random Subspace Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory

A Benchmark for Cross-Domain Argumentative Stance Classification on Social Media

Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies

Measuring the Inconsistency of Large Language Models in Preferential Ranking

Do Unlearning Methods Remove Information from Language Model Weights?

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models