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 7, 2024

Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models
Dahyun Kim, Sukyung Lee, Yungi Kim, Attapol Rutherford, Chanjun Park
Large Language Model Thai Language
Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
Jiahuan Li, Yiqing Cao, Shujian Huang, Jiajun Chen
Large Language Model Raw Data Large Pre Trained Model Knowledge Intensive Task Fast Learning Learning Preference
Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM
Tianhui Cai, Yifan Liu, Zewei Zhou, Haoxuan Ma, Seth Z. Zhao, Zhiwen Wu, Jiaqi Ma
Large Language Model Autonomous Vehicle Retrieval Augmented Social Medium Regulation Traffic Rule Explainable Decision
$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization
Dylan Zhang, Justin Wang, Francois Charton
Large Language Model Strong Generalization Instruction Following Generalist Model Diverse Instruction
Rule-based Data Selection for Large Language Models
Xiaomin Li, Mingye Gao, Zhiwei Zhang, Chang Yue, Hong Hu
Large Language Model Data Selection Human Rating Preference Rating Decision Rule
The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?
Alexander S. Choi, Syeda Sabrina Akter, JP Singh, Antonios Anastasopoulos
Large Language Model Real Human Topic Detection Expert Annotation Human LLM
MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
Lei Wang, Shan Dong, Yuhui Xu, Hanze Dong, Yalu Wang, Amrita Saha, Ee-Peng Lim, Caiming Xiong, Doyen Sahoo
Large Language Model Long Context Mathematical Reasoning Recent Large Language Model
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
Qingyu Yin, Xuzheng He, Luoao Deng, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang
Large Language Model Fine Tuning Context Learning Real Power Different Context Information System Update Bug Pattern Attribute Pattern
Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debates
Chaithanya Bandi, Abir Harrasse
Large Language Model Multi Agent Probabilistic Model Adversarial Text

October 6, 2024

Control Large Language Models via Divide and Conquer
Bingxuan Li, Yiwei Wang, Tao Meng, Kai-Wei Chang, Nanyun Peng
Large Language Model Text Generation Controllable Generation Data Divide Constrained Generation Lexical Constraint
Evaluation of Code LLMs on Geospatial Code Generation
Piotr Gramacki, Bruno Martins, Piotr Szymański
Large Language Model Global Evaluation Code Generation Geospatial Data Code Generation Model
ProtocoLLM: Automatic Evaluation Framework of LLMs on Domain-Specific Scientific Protocol Formulation Tasks
Seungjun Yi, Jaeyoung Lim, Juyong Yoon
Large Language Model Automatic Evaluation Population Protocol Scientific Workflow Protocol Design
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Qiqiang Lin, Muning Wen, Qiuying Peng, Guanyu Nie, Junwei Liao, Jun Wang, Xiaoyun Mo, Jiamu Zhou, Cheng Cheng, Yin Zhao, Jun Wang, Weinan Zhang
Large Language Model Language Model Robust Generalization Enhancing Generalization Function Calling Model Developer
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
Aakriti Agrawal, Mucong Ding, Zora Che, Chenghao Deng, Anirudh Satheesh, John Langford, Furong Huang
Large Language Model Strong Generalization Diverse Ensemble Weak to Strong Adaboost Algorithm
On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective
Shoaib Ahmed Siddiqui, Yanzhi Chen, Juyeon Heo, Menglin Xia, Adrian Weller
Large Language Model Capability Evolution Bayesian Perspective Model Capability Model Generation Functional Model
RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference
Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao
Large Language Model Natural Language Processing LLM Inference Adapter Module Data Multiplexing
Realizing Video Summarization from the Path of Language-based Semantic Understanding
Kuan-Chen Mu, Zhi-Yi Chin, Wei-Chen Chiu
Large Language Model Root to Leaf Path Video Summarization Semantic Understanding Text Summary
Diagnosing Robotics Systems Issues with Large Language Models
Jordis Emilia Herrmann, Aswath Mandakath Gopinath, Mikael Norrlof, Mark Niklas Müller
Large Language Model Robotics Domain Robotic System Root Cause Diagnostic Reasoning Benchmark
MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems
Zhentao Xie, Jiabao Zhao, Yilei Wang, Jinxin Shi, Yanhong Bai, Xingjiao Wu, Liang He
Large Language Model Language Model Multi Agent System Multi Turn Dialogue Cognitive Bias
Lens: Rethinking Multilingual Enhancement for Large Language Models
Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Ting Liu
Large Language Model Camera Lens Multilingual Capability

Large Language Model

Papers

Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models

Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge

Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

Rule-based Data Selection for Large Language Models

The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning

Adversarial Multi-Agent Evaluation of Large Language Models through Iterative Debates

Control Large Language Models via Divide and Conquer

Evaluation of Code LLMs on Geospatial Code Generation

ProtocoLLM: Automatic Evaluation Framework of LLMs on Domain-Specific Scientific Protocol Formulation Tasks

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?

On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective

RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference

Realizing Video Summarization from the Path of Language-based Semantic Understanding

Diagnosing Robotics Systems Issues with Large Language Models

MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems

Lens: Rethinking Multilingual Enhancement for Large Language Models