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 3, 2024

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
Patara Trirat, Wonyong Jeong, Sung Ju Hwang
Large Language Model Online autoML AutoML System AI Pipeline AutoML Pipeline
LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences
Zhenxiao Fu, Fan Chen, Shan Zhou, Haitong Li, Lei Jiang
Large Language Model Efficient Inference Large Language Model Inference Carbon Footprint
Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice
Haiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao, Yuheng Bu
Large Language Model Adversarial Attack Theoretical Understanding Watermarking Scheme
Position: LLM Unlearning Benchmarks are Weak Measures of Progress
Pratiksha Thaker, Shengyuan Hu, Neil Kale, Yash Maurya, Zhiwei Steven Wu, Virginia Smith
Large Language Model Unlearning Framework Much Progress Random Walk Product Specific Position Information Unlearning Method Unlearned Model Unlearning Model
SIEVE: General Purpose Data Filtering System Matching GPT-4o Accuracy at 1% the Cost
Jifan Zhang, Robert Nowak
Large Language Model Language Model Domain Specific Hidden CoST Bio Sieve
Neutral residues: revisiting adapters for model extension
Franck Signe Talla, Herve Jegou, Edouard Grave
Large Language Model Domain Adaptation Fine Tuning Adapter Module Model Improvement Weight Freezing
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
Yekun Chai, Haoran Sun, Huang Fang, Shuohuan Wang, Yu Sun, Hua Wu
Large Language Model Reinforcement Learning Human Feedback Reinforcement Learning From Human Feedback
Grounding Large Language Models In Embodied Environment With Imperfect World Models
Haolan Liu, Jishen Zhao
Large Language Model Multi Agent World Model Embodied Environment
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
Rohin Manvi, Anikait Singh, Stefano Ermon
Large Language Model Inference Time Adversarial Reward Best of N
Large Language Models as Markov Chains
Oussama Zekri, Ambroise Odonnat, Abdelhakim Benechehab, Linus Bleistein, Nicolas Boullé, Ievgen Redko
Large Language Model Language Model Markov Chain Generalization Error Bound
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Hadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart, Idan Szpektor, Hadas Kotek, Yonatan Belinkov
Large Language Model Internal Representation Error Detection LLM Hallucination Reasoning Error
CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs
Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
Large Language Model Diverse Set Task Complexity Challenging Benchmark Intangible Cultural Heritage
Hate Personified: Investigating the role of LLMs in content moderation
Sarah Masud, Sahajpreet Singh, Viktor Hangya, Alexander Fraser, Tanmoy Chakraborty
Large Language Model Medical LLM Integral Role Hate Speech Personality Trait Content Moderation High Performance Hate Localization Cue
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek F. Wong, Rui Wang
Large Language Model Chain of Thought Benchmark Platform Domain Translation
Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
Yun Qu, Boyuan Wang, Yuhang Jiang, Jianzhun Shao, Yixiu Mao, Cheems Wang, Chang Liu, Xiangyang Ji
Large Language Model Reinforcement Learning Action Space Value Laden Choice Manual Effort Multi Agent Exploration
Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang, Jun Lin, Kaisong Song, tianqianjin lin, Pengwei Yan, Changlong Sun, Xiaozhong Liu
Large Language Model DCU Insight AQ Multi Agent Collaboration Legal Reasoning Reasoning Problem Legal Task
Dual Active Learning for Reinforcement Learning from Human Feedback
Pangpang Liu, Chengchun Shi, Will Wei Sun
Large Language Model Reinforcement Learning Offline Reinforcement Learning Human Feedback Reward Report Dual Learning Reward Estimator
Defining Knowledge: Bridging Epistemology and Large Language Models
Constanza Fierro, Ruchira Dhar, Filippos Stamatiou, Nicolas Garneau, Anders Søgaard
Large Language Model Knowledge Based Epistemic Space
Dynamic Gradient Alignment for Online Data Mixing
Simin Fan, David Grangier, Pierre Ablin
Large Language Model Gradient Alignment Data Mixing
Encryption-Friendly LLM Architecture
Donghwan Rho, Taeseong Kim, Minje Park, Jung Woo Kim, Hyunsik Chae, Jung Hee Cheon, Ernest K. Ryu
Large Language Model Transformer Architecture Privacy Preserving Homomorphic Encryption Encrypted Model

Large Language Model

Papers

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences

Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice

Position: LLM Unlearning Benchmarks are Weak Measures of Progress

SIEVE: General Purpose Data Filtering System Matching GPT-4o Accuracy at 1% the Cost

Neutral residues: revisiting adapters for model extension

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

Grounding Large Language Models In Embodied Environment With Imperfect World Models

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Large Language Models as Markov Chains

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs

Hate Personified: Investigating the role of LLMs in content moderation

Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

Dual Active Learning for Reinforcement Learning from Human Feedback

Defining Knowledge: Bridging Epistemology and Large Language Models

Dynamic Gradient Alignment for Online Data Mixing

Encryption-Friendly LLM Architecture