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

November 18, 2024

Understanding Chain-of-Thought in LLMs through Information Theory
Jean-Francois Ton, Muhammad Faaiz Taufiq, Yang Liu
Large Language Model Chain of Thought Reasoning Task Information Theory
Bi-Mamba: Towards Accurate 1-Bit State Space Models
Shengkun Tang, Liqun Ma, Haonan Li, Mingjie Sun, Zhiqiang Shen
Large Language Model State Space Model Inference Memory Usage Autoregressive Distillation
Tackling prediction tasks in relational databases with LLMs
Marek Wydmuch, Łukasz Borchmann, Filip Graliński
Large Language Model Prediction Task Relational Database Relation Information
LLM-IE: A Python Package for Generative Information Extraction with Large Language Models
Enshuo Hsu, Kirk Roberts
Large Language Model Medical LLM Entity Recognition Python Library Generative Information Extraction
BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration
Yuzong Chen, Ahmed F. AbouElhamayed, Xilai Dai, Yang Wang, Marta Andronic, George A. Constantinides, Mohamed S. Abdelfattah
Large Language Model LLM Quantization
Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
Allison Huang, Yulu Niki Pi, Carlos Mougan
Large Language Model Moral Dilemma Persuasive Capability
Enhancing LLM Reasoning with Reward-guided Tree Search
Jinhao Jiang, Zhipeng Chen, Yingqian Min, Jie Chen, Xiaoxue Cheng, Jiapeng Wang, Yiru Tang, Haoxiang Sun, Jia Deng, Wayne Xin Zhao, Zheng Liu, Dong Yan, Jian Xie, Zhongyuan Wang, Ji-Rong Wen
Large Language Model Reasoning Task Technical Report LLM Reasoning Reward Tree
AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning
Kun Xiang, Zhili Liu, Zihao Jiang, Yunshuang Nie, Runhui Huang, Haoxiang Fan, Hanhui Li, Weiran Huang, Yihan Zeng, Jianhua Han, Lanqing Hong, Hang Xu, Xiaodan Liang
Large Language Model Complex Reasoning Atomic Knowledge Large Scale Multimodal Multimodal Mathematical
FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training
Anjia Cao, Xing Wei, Zhiheng Ma
Large Language Model Text to Image Retrieval Frozen Large Language Model Efficient Image Language Image Pre Training Long Context Retrieval
Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation
Peng Shu, Junhao Chen, Zhengliang Liu, Hui Wang, Zihao Wu, Tianyang Zhong, Yiwei Li, Huaqin Zhao, Hanqi Jiang, Yi Pan, Yifan Zhou, Constance Owl, Xiaoming Zhai, Ninghao Liu, Claudio Saunt, Tianming Liu
Large Language Model Low Resource Language Low Resource Translation Quality Human Translation Linguistic Landscape
LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models
Yungi Kim, Hyunsoo Ha, Seonghoon Yang, Sukyung Lee, Jihoo Kim, Chanjun Park
Large Language Model Language Model Lightweight High Large Scale Datasets Data Pipeline
Large corpora and large language models: a replicable method for automating grammatical annotation
Cameron Morin, Matti Marttinen Larsson
Large Language Model Large Corpus Linguistic Study Linguistic Annotation Replication Study
ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification
Son T. Luu, Hiep Nguyen, Trung Vo, Le-Minh Nguyen
Large Language Model Zero Shot Fact Verification Task Fact Checking Model Multi Hop Fact Verification Verification Strategy
MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs
Shiyi Cao, Shu Liu, Tyler Griggs, Peter Schafhalter, Xiaoxuan Liu, Ying Sheng, Joseph E. Gonzalez, Matei Zaharia, Ion Stoica
Large Language Model Inference Task Dense Model GPU Memory Batch Inference

November 17, 2024

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text
Weiqing He, Bojian Hou, Tianqi Shang, Davoud Ataee Tarzanagh, Qi Long, Li Shen
Large Language Model LLM Generated Text Semantics Human Engineered Word Sequence Semantic Framework
TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models
Tingyu Qu, Mingxiao Li, Tinne Tuytelaars, Marie-Francine Moens
Large Language Model Pre Trained Training Free Visual Token Video Understanding Task Video LLM
Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text
Xiaoliang Luo, Michael Ramscar, Bradley C. Love
Large Language Model Transformer Based Human Language Human Like Language Processing Structured Input Complex Scientific
FastDraft: How to Train Your Draft
Ofir Zafrir, Igor Margulis, Dorin Shteyman, Guy Boudoukh
Large Language Model Speculative Decoding Draft Model K$ Draft
SRA-MCTS: Self-driven Reasoning Aurmentation with Monte Carlo Tree Search for Enhanced Code Generation
Bin Xu, Yiguan Lin, Yinghao Li, YangGao
Large Language Model Language Model Code Generation Search Query Reasoning Path Augmented Data Minimax McTs Self Reasoning
Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph
Menghan Wang, Yuchen Guo, Duanfeng Zhang, Jianian Jin, Minnie Li, Dan Schonfeld, Shawn Zhou
Large Language Model Effective Recommendation E Commerce Explainable Recommendation Service Discovery Product Understanding

Large Language Model

Papers

Understanding Chain-of-Thought in LLMs through Information Theory

Bi-Mamba: Towards Accurate 1-Bit State Space Models

Tackling prediction tasks in relational databases with LLMs

LLM-IE: A Python Package for Generative Information Extraction with Large Language Models

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment

Enhancing LLM Reasoning with Reward-guided Tree Search

AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning

FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation

LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models

Large corpora and large language models: a replicable method for automating grammatical annotation

ZeFaV: Boosting Large Language Models for Zero-shot Fact Verification

MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text

FastDraft: How to Train Your Draft

SRA-MCTS: Self-driven Reasoning Aurmentation with Monte Carlo Tree Search for Enhanced Code Generation

Enabling Explainable Recommendation in E-commerce with LLM-powered Product Knowledge Graph