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

December 20, 2024

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
Brian J Chan, Chao-Ting Chen, Jui-Hung Cheng, Hen-Hsen Huang
Large Language Model Language Model Retrieval Augmented Generation Task Specific Knowledge Long Context Large Language Model
In-context Continual Learning Assisted by an External Continual Learner
Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, Bing Liu
Large Language Model Continual LEArning Context Learning Complex Prompt Lifelong Learning
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
Zhenjie Xu (1), Wenqing Chen (1), Yi Tang (1), Xuanying Li (2), Cheng Hu (1), Zhixuan Chu (3), Kui Ren (3), Zibin Zheng (1), Zhichao Lu (4) ((1) School of Software Engineering, Sun Yat-sen University, (2) School of Physics and Astronomy, Sun Yat-sen University, (3) School of Cyber Science and Technology, Zhejiang University, (4) Department of Computer Science, City University of Hong Kong)
Large Language Model Natural Language Processing Constructive Approach Social Bias Multi Agent Framework Bias Score
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
Large Language Model Full Model Supervised Fine Tuning Large Scale Datasets Closed Source Large Language Model Tool Usage Feature Model Training Stage
Continual Learning Using Only Large Language Model Prompting
Jiabao Qiu, Zixuan Ke, Bing Liu
Large Language Model Language Model LeArning Abstract Continual LEArning Continual Learning Text Summarization

December 19, 2024

Why Do Large Language Models (LLMs) Struggle to Count Letters?
Tairan Fu, Raquel Ferrando, Javier Conde, Carlos Arriaga, Pedro Reviriego
Large Language Model Attention Mechanism Automatic Counting Word Frequency
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
Tianchen Zhang, Gururaj Saileshwar, David Lie
Large Language Model Language Model Time Matter Side Channel Prompt Based
Systematic Evaluation of Long-Context LLMs on Financial Concepts
Lavanya Gupta, Saket Sharma, Yiyun Zhao
Large Language Model Context Length Task Complexity Real World Task Long Context LLM Financial Domain Task Instruction
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei
Large Language Model New Benchmark Multiple Choice Massive Multitask Language Understanding
HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages
Aman Chaturvedi, Daniel Nichols, Siddharth Singh, Abhinav Bhatele
Large Language Model Low Resource High Performance Computing Code LLM High Performance Computing System Parallel Code
Adaptive Pruning for Large Language Models with Structural Importance Awareness
Haotian Zheng, Jinke Ren, Yushan Sun, Ruichen Zhang, Wenbo Zhang, Zhen Li, Dusit Niyato, Shuguang Cui, Yatong Han
Large Language Model Text Generation Inner Structure Model Pruning Social Awareness Adaptive Pruning
Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture
Thomas F Burns, Tomoki Fukai, Christopher J Earls
Large Language Model Context Learning Neural Architecture Large Relevance Improvement Associative Memory Residual Stream Associative Memory Model
ConfliBERT: A Language Model for Political Conflict
Patrick T. Brandt, Sultan Alsarra, Vito J. D`Orazio, Dagmar Heintze, Latifur Khan, Shreyas Meher, Javier Osorio, Marcus Sianan
Large Language Model Language Model Human Generated Communal Violence Political Event
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
Felix Friedrich, Simone Tedeschi, Patrick Schramowski, Manuel Brack, Roberto Navigli, Huu Nguyen, Bo Li, Kristian Kersting
Large Language Model View Translation Multilingual Benchmark Multiple Language Alert System Multilingual Safety
Knowledge Injection via Prompt Distillation
Kalle Kujanpää, Harri Valpola, Alexander Ilin
Large Language Model Knowledge Injection Prompt Distillation
Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation
Zexiong Ma, Shengnan An, Zeqi Lin, Yanzhen Zou, Jian-Guang Lou, Bing Xie
Large Language Model Faithful Generation Negative Learning
Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
Junyi Li, Hwee Tou Ng
Large Language Model Text Generation Search Query Monte Carlo Tree Search Reward Model Multi Step Reasoning Much Progress Tree Based
DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
Hongling Xu, Yice Zhang, Qianlong Wang, Ruifeng Xu
Large Language Model Aspect Based Sentiment Analysis Diverse Datasets Data Synthesis LLM Generation Label Refinement
Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
Greta Dolcetti, Vincenzo Arceri, Eleonora Iotti, Sergio Maffeis, Agostino Cortesi, Enea Zaffanella
Large Language Model Code Generation Human Feedback Open Source Large Language Model Level Test Static Analysis
ResoFilter: Rine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li
Large Language Model Fine Tuning Full Model Synthetic Data Large Language Data Augmentation Method Data Augmentation Technique Acoustic Resonance Pressure Filtration

Large Language Model

Papers

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks

In-context Continual Learning Assisted by an External Continual Learner

Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Continual Learning Using Only Large Language Model Prompting

Why Do Large Language Models (LLMs) Struggle to Count Letters?

Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models

Systematic Evaluation of Long-Context LLMs on Financial Concepts

MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark

HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages

Adaptive Pruning for Large Language Models with Structural Importance Awareness

Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture

ConfliBERT: A Language Model for Political Conflict

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps

Knowledge Injection via Prompt Distillation

Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation

Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling

DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis

Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis

ResoFilter: Rine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis