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 10, 2024

Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models
Sultan Alrashed, Dmitrii Khizbullin, David R. Pugh
Large Language Model Language Model Machine Translation Large Corpus Multilingual Large Language Model Machine Translated Arabic Language
Self-Training Meets Consistency: Improving LLMs' Reasoning With Consistency-Driven Rationale Evaluation
Jaehyeok Lee, Keisuke Sakaguchi, JinYeong Bak
Large Language Model Complex Reasoning Self Training Reasoning Ability Self Rationalization

November 9, 2024

Quasi-random Multi-Sample Inference for Large Language Models
Aditya Parashar, Aditya Vikram Singh, Avinash Amballa, Jinlin Lai, Benjamin Rozonoyer
Large Language Model Sampling Based
Robust Detection of LLM-Generated Text: A Comparative Analysis
Yongye Su, Yuqing Wu
Large Language Model Text Modality Comparative Study Support Vector Machine LLM Generated Robust Detection Naive Bayes
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization
Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang, Yongbin Li
Large Language Model Instruction Following Preference Optimization Instruction Dataset Complex Instruction Instruction Datasets Diverse Instruction
Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust
Vera Pavlova, Mohammed Makhlouf
Large Language Model Natural Language Processing Internet Service Domain Arabic Speaker MultiLingual Information Retrieval
Detecting Reference Errors in Scientific Literature with Large Language Models
Tianmai M. Zhang, Neil F. Abernethy
Large Language Model Full Model Large Language Higher Quality Reference Scientific Literature Quotation Attribution Scientific Publishing Hidden Citation
Personalized News Recommendation System via LLM Embedding and Co-Occurrence Patterns
Zheng Li, Kai Zhange
Large Language Model Medical LLM Co Occurrence News Recommendation LLM Embeddings
A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization
Haoxin Liu, Chenghao Liu, B. Aditya Prakash
Large Language Model Time Series Time Matter Interactive Visualization Natural Language Reasoning TV Show Prompt Based Method Web Screenshots

November 8, 2024

The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
Wiktoria Mieleszczenko-Kowszewicz, Dawid Płudowski, Filip Kołodziejczyk, Jakub Świstak, Julian Sienkiewicz, Przemysław Biecek
Large Language Model Personality Trait Linguistic Feature Cognitive Process Persuasive Capability Big Five Personality
Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM
Haizhou Wang, Nanqing Luo, Peng LIu
Large Language Model Quantum Shadow Reverse Engineering Malware Analysis Implementation Detail Malware Sample Analytical Method
Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation
Aayush Shah, Shankar Jayaratnam
Large Language Model Full Model Low Resource Language Protein Language Model Low Rank Adapter Protein Sequence Generation
Recycled Attention: Efficient inference for long-context language models
Fangyuan Xu, Tanya Goyal, Eunsol Choi
Large Language Model Efficient Inference Information Redundancy Long Context Language Long Input Context
Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?
Veronica Chatrath, Marcelo Lotif, Shaina Raza
Large Language Model Fake News Fact Checking Multi FAct Annotation Bias Fictional Language
Multi-hop Evidence Pursuit Meets the Web: Team Papelo at FEVER 2024
Christopher Malon
Large Language Model Reasoning Capability Evidence Piece Multi Hop Question Generation Method
Humans Continue to Outperform Large Language Models in Complex Clinical Decision-Making: A Study with Medical Calculators
Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong, Serina Applebaum, Aidan Gilson, Reid McMurry, R. Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu
Large Language Model Real Human Decision Making
Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages
JA Meaney, Beatrice Alex, William Lamb
Large Language Model Low Resource Language Digital Humanity Fairy Tale
Assessing the Answerability of Queries in Retrieval-Augmented Code Generation
Geonmin Kim, Jaeyeon Kim, Hancheol Park, Wooksu Shin, Tae-Ho Kim
Large Language Model Natural Language Code Generation Faithful Generation Query Information
An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking
Zijian Chen, Ronak Pradeep, Jimmy Lin
Large Language Model Zero Shot Large Relevance Improvement Ranking Model TREC Evaluation Listwise Rerankers
KyrgyzNLP: Challenges, Progress, and Future
Anton Alekseev, Timur Turatali
Large Language Model Natural Language Processing Technical Challenge Future Reasoning Much Progress High Resource Language Resourced Language

Large Language Model

Papers

Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models

Self-Training Meets Consistency: Improving LLMs' Reasoning With Consistency-Driven Rationale Evaluation

Quasi-random Multi-Sample Inference for Large Language Models

Robust Detection of LLM-Generated Text: A Comparative Analysis

IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization

Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust

Detecting Reference Errors in Scientific Literature with Large Language Models

Personalized News Recommendation System via LLM Embedding and Co-Occurrence Patterns

A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization

The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses

Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM

Energy Efficient Protein Language Models: Leveraging Small Language Models with LoRA for Controllable Protein Generation

Recycled Attention: Efficient inference for long-context language models

Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?

Multi-hop Evidence Pursuit Meets the Web: Team Papelo at FEVER 2024

Humans Continue to Outperform Large Language Models in Complex Clinical Decision-Making: A Study with Medical Calculators

Evaluating and Adapting Large Language Models to Represent Folktales in Low-Resource Languages

Assessing the Answerability of Queries in Retrieval-Augmented Code Generation

An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking

KyrgyzNLP: Challenges, Progress, and Future