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 23, 2024

Factuality or Fiction? Benchmarking Modern LLMs on Ambiguous QA with Citations
Maya Patel, Aditi Anand
Large Language Model Question Answering Factual Claim Software Citation Citation Pattern Citation Generation Fictional Language
Trustworthy and Efficient LLMs Meet Databases
Kyoungmin Kim, Anastasia Ailamaki
Large Language Model New Database
StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs
Hailin Chen, Fangkai Jiao, Mathieu Ravaut, Nawshad Farruque, Xuan Phi Nguyen, Chengwei Qin, Manan Dey, Bosheng Ding, Caiming Xiong, Shafiq Joty, Yingbo Zhou
Large Language Model Complex Reasoning Structured Output Compositional Ability Model Based Evaluation
CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
Ruibo Tu, Hedvig Kjellström, Gustav Eje Henter, Cheng Zhang
Large Language Model Full Model Causal Graph Large Language Causal Reasoning LLM Benchmark
BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism
Martin Fajcik, Martin Docekal, Jan Dolezal, Karel Ondrej, Karel Beneš, Jan Kapsa, Pavel Smrz, Alexander Polok, Michal Hradis, Zuzana Neverilova, Ales Horak, Radoslav Sabol, Michal Stefanik, Adam Jirkovsky, David Adamczyk, Petr Hyner, Jan Hula, Hynek Kydlicek
Large Language Model Language Model Dimensional Benchmark
Deliberation in Latent Space via Differentiable Cache Augmentation
Luyang Liu, Jonas Pfeiffer, Jiaxing Wu, Jun Xie, Arthur Szlam
Large Language Model Language Model Latent Space Complex Reasoning Task Language Modeling Loss Political Deliberation
YuLan-Mini: An Open Data-efficient Language Model
Yiwen Hu, Huatong Song, Jia Deng, Jiapeng Wang, Jie Chen, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Wayne Xin Zhao, Ji-Rong Wen
Large Language Model Language Model Pre Training Long Context
Large Language Model Safety: A Holistic Survey
Dan Shi, Tianhao Shen, Yufei Huang, Zhigen Li, Yongqi Leng, Renren Jin, Chuang Liu, Xinwei Wu, Zishan Guo, Linhao Yu, Ling Shi, Bojian Jiang, Deyi Xiong
Large Language Model Artificial Intelligence Language Understanding Comprehensive Survey Artificial Intelligence Governance AI Risk
SCBench: A Sports Commentary Benchmark for Video LLMs
Kuangzhi Ge, Lingjun Chen, Kevin Zhang, Yulin Luo, Tianyu Shi, Liaoyuan Fan, Xiang Li, Guanqun Wang, Shanghang Zhang
Large Language Model Video LLM Benchmark Data
Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
Yang Xu, Yi Wang, Hao Wang
Large Language Model Supervised Autoencoder Mechanistic Interpretability LLM Training Dynamic Feature Software Evolution Mechanistic Study Feature Drift
Emerging Security Challenges of Large Language Models
Herve Debar, Sven Dietrich, Pavel Laskov, Emil C. Lupu, Eirini Ntoutsi
Large Language Model Adversarial Attack Machine Learning Model Traditional Machine Learning Security Challenge
LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context
Kai Ruan, Xuan Wang, Jixiang Hong, Peng Wang, Yang Liu, Hao Sun
Large Language Model Faithful Generation Context Information Sustained Creativity Human Generated Idea Divergent Thinking
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference
Chao Zeng, Songwei Liu, Shu Yang, Fangmin Chen, Xing Mei, Lean Fu
Large Language Model Many Sparse Sparsity Increase Large Language Model Inference Dynamic Sparse Training
Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing
Prakash Aryan
Large Language Model Language Model Level Test Model Adaptation Arabic Natural Language Processing Language Adaptation
A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
Shuaihang Chen, Yuanxing Liu, Wei Han, Weinan Zhang, Ting Liu
Large Language Model Timely Survey Multi Agent Recent Advance New Frontier Complex Task Generative Agent
Measuring Contextual Informativeness in Child-Directed Text
Maria Valentini, Téa Wright, Ali Marashian, Jennifer Weber, Eliana Colunga, Katharina von der Wense
Large Language Model Nine Year Old Child Automatic Evaluation Older Adult Content Enrichment
Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning
Huchen Jiang, Yangyang Ma, Chaofan Ding, Kexin Luan, Xinhan Di
Large Language Model Monte Carlo Tree Search Preference Learning Self Correction Cognitive Reasoning Iterative Preference Learning
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models
Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
Large Language Model Language Model Training Data Fine Tuned Judge Model
Interweaving Memories of a Siamese Large Language Model
Xin Song, Zhikai Xue, Guoxiu He, Jiawei Liu, Wei Lu
Large Language Model Parameter Efficient Fine Tuning Personal Memory Memory Augmentation
A Dual-Perspective Metaphor Detection Framework Using Large Language Models
Yujie Lin, Jingyao Liu, Yan Gao, Ante Wang, Jinsong Su
Large Language Model Natural Language Processing Full Model Large Language Metaphor Detection Metaphor Use

Large Language Model

Papers

Factuality or Fiction? Benchmarking Modern LLMs on Ambiguous QA with Citations

Trustworthy and Efficient LLMs Meet Databases

StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs

CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models

BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism

Deliberation in Latent Space via Differentiable Cache Augmentation

YuLan-Mini: An Open Data-efficient Language Model

Large Language Model Safety: A Holistic Survey

SCBench: A Sports Commentary Benchmark for Video LLMs

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study

Emerging Security Challenges of Large Language Models

LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context

GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference

Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing

A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application

Measuring Contextual Informativeness in Child-Directed Text

Towards Intrinsic Self-Correction Enhancement in Monte Carlo Tree Search Boosted Reasoning via Iterative Preference Learning

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models

Interweaving Memories of a Siamese Large Language Model

A Dual-Perspective Metaphor Detection Framework Using Large Language Models