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 1, 2024

Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection
Zhipeng Wei, Yuqi Liu, N. Benjamin Erichson
Large Language Model Data Detection Practical Method Jailbreak Attack Token Embeddings Token Bias Safety Risk
Privacy Risks of Speculative Decoding in Large Language Models
Jiankun Wei, Abdulrahman Abdulrazzag, Tianchen Zhang, Adel Muursepp, Gururaj Saileshwar
Large Language Model Privacy Risk Speculative Decoding Token Generation Privacy Breach
AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs
Varun Badrinath Krishna
Large Language Model Data Set Retrieval Augmented Generation Domain Specific Open Source Large Language Model
InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation
Marcos Macedo, Yuan Tian, Pengyu Nie, Filipe R. Cogo, Bram Adams
Large Language Model Feature Enhancement Code Translation
FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models
Jiaqi Wu, Simin Chen, Yuzhe Yang, Yijiang Li, Shiyue Hou, Rui Jing, Zehua Wang, Wei Chen, Zijian Tian
Large Language Model Natural Language Processing Black Box Prompt Tuning Prompt Optimization Federated Foundation Model
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian, Chun-Sung Ferng, Heinrich Jiang, Yiran Chen
Large Language Model Language Model Reasoning Task Factual Claim Latent Concept Self Evolution
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
Yiwen Ding, Zhiheng Xi, Wei He, Zhuoyuan Li, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
Large Language Model Complex Reasoning Open Sampling Self Improvement LLM Policy Self Improving
LLMs: A Game-Changer for Software Engineers?
Md Asraful Haque
Large Language Model Software Engineering AI Application Complex Model
MolCap-Arena: A Comprehensive Captioning Benchmark on Language-Enhanced Molecular Property Prediction
Carl Edwards, Ziqing Lu, Ehsan Hajiramezanali, Tommaso Biancalani, Heng Ji, Gabriele Scalia
Large Language Model Molecular Property Prediction Molecular Property Captioning Benchmark Arena Hard
Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis
Linda Zeng
Large Language Model Natural Language Processing Synthetic Data Sentiment Analysis Code Mixed Code Mixing Mixed Sample Data Augmentation
ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models
Anbang Wang
Large Language Model Zero Shot Entity Recognition Exemplar Based Reverse Noise
Active Preference-based Learning for Multi-dimensional Personalization
Minhyeon Oh, Seungjoon Lee, Jungseul Ok
Large Language Model LeArning Abstract Preference Feedback Human Preference Preference Learning Generating User Activity Scalable Personalization Binary Feedback
Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
Do Xuan Long, Duong Ngoc Yen, Anh Tuan Luu, Kenji Kawaguchi, Min-Yen Kan, Nancy F. Chen
Large Language Model Human SAFETY Multiple Expert Automatic Usefulness Prediction
Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model
Subhadip Nandi, Neeraj Agrawal
Large Language Model Language Model Entity Recognition Cross Domain Word Embeddings Human Instruction Cross Domain NER
Chat Bankman-Fried: an Exploration of LLM Alignment in Finance
Claudia Biancotti, Carolina Camassa, Andrea Coletta, Oliver Giudice, Aldo Glielmo
Large Language Model Artificial Intelligence Environment Exploration AI Safety LLM Alignment E Chat
E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
Yun Jiang, Zilong Xie, Wei Zhang, Yun Fang, Shuai Pan
Large Language Model Retrieval Augmented Generation Text Generation External Knowledge End to End Model Adaptive Filter End 2 End
Self-Evolved Reward Learning for LLMs
Chenghua Huang, Zhizhen Fan, Lu Wang, Fangkai Yang, Pu Zhao, Zeqi Lin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Large Language Model Language Model Reinforcement Learning Reward Model Self Feedback

Large Language Model

Papers

CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research

Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

How Effective Is Self-Consistency for Long-Context Problems?

Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection

Privacy Risks of Speculative Decoding in Large Language Models

AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs

InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation

FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling

LLMs: A Game-Changer for Software Engineers?

MolCap-Arena: A Comprehensive Captioning Benchmark on Language-Enhanced Molecular Property Prediction

Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis

ReverseNER: A Self-Generated Example-Driven Framework for Zero-Shot Named Entity Recognition with Large Language Models

Active Preference-based Learning for Multi-dimensional Personalization

Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models

Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model

Chat Bankman-Fried: an Exploration of LLM Alignment in Finance

E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation

Self-Evolved Reward Learning for LLMs