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 12, 2024

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
Khaoula Chehbouni, Jonathan Colaço-Carr, Yash More, Jackie CK Cheung, Golnoosh Farnadi
Large Language Model Human Feedback
Challenges in Guardrailing Large Language Models for Science
Nishan Pantha, Muthukumaran Ramasubramanian, Iksha Gurung, Manil Maskey, Rahul Ramachandran
Large Language Model Natural Language Processing Technical Challenge NLP Field Science Journalism Scientific Domain
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King
Large Language Model Knowledge Graph Complex Reasoning App to App Retrieval Knowledge Graph Completion Context Modeling Semantic Gap Ranking Step
Large Language Models Can Self-Improve in Long-context Reasoning
Siheng Li, Cheng Yang, Zesen Cheng, Lemao Liu, Mo Yu, Yujiu Yang, Wai Lam
Large Language Model Long Context Supervised Fine Tuning Long Context Scenario
Can adversarial attacks by large language models be attributed?
Manuel Cebrian, Jan Arne Telle
Large Language Model Adversarial Attack Attribution Score Formal Language LLM Attack
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
Yiyang Ma, Xingchao Liu, Xiaokang Chen, Wen Liu, Chengyue Wu, Zhiyu Wu, Zizheng Pan, Zhenda Xie, Haowei Zhang, Xingkai yu, Liang Zhao, Yisong Wang, Jiaying Liu, Chong Ruan
Large Language Model Vision Language Model Generative Modeling Faithful Generation Autoregressive Model Autoregressive Language Model Multimodal Understanding Image Understanding Rectified Flow
Verbosity $\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models
Yusen Zhang, Sarkar Snigdha Sarathi Das, Rui Zhang
Large Language Model Model Generated Long Form Answer Simplicity Bias
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
Philip Zmushko, Aleksandr Beznosikov, Martin Takáč, Samuel Horváth
Large Language Model Low Rank Memory Efficient Gradient Projection Scalable Training Dependent Cost
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
Youan Cong, Cheng Wang, Pritom Saha Akash, Kevin Chen-Chuan Chang
Large Language Model Retrieval Augmented Generation Parametric Knowledge Query Optimization
ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
Weibo Zhao, Yubin Shi, Xinyu Lyu, Wanchen Sui, Shen Li, Yong Li
Large Language Model Large Language Quantization Error Activation Quantization Model Quantization Reconstruction Error State of the Art Quantization
Training Data for Large Language Model
Yiming Ju, Huanhuan Ma
Large Language Model Artificial Intelligence Training Data ChatGPT Generated Conversation High Quality Large Scale Language Model Human Annotated
World Models: The Safety Perspective
Zifan Zeng, Chongzhe Zhang, Feng Liu, Joseph Sifakis, Qunli Zhang, Shiming Liu, Peng Wang
Large Language Model Artificial Intelligence AI Agent World Model Agent System
Top-$nσ$: Not All Logits Are You Need
Chenxia Tang, Jianchun Liu, Hongli Xu, Liusheng Huang
Large Language Model Reasoning Datasets Second Ranked Logits Greedy Decoding Temperature Sampling
Direct Preference Optimization Using Sparse Feature-Level Constraints
Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang
Large Language Model Direct Preference Optimization Preference Optimization LLM Alignment Sparsity Constraint
Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations
Rose E. Wang, Pawan Wirawarn, Kenny Lam, Omar Khattab, Dorottya Demszky
Large Language Model Case Study App to App Retrieval Community Conversation Conversation Dynamic Human Tutor
Entropy Controllable Direct Preference Optimization
Motoki Omura, Yasuhiro Fujita, Toshiki Kataoka
Large Language Model Reinforcement Learning Direct Preference Optimization KL Divergence Binary Cross Entropy
Model Stealing for Any Low-Rank Language Model
Allen Liu, Ankur Moitra
Large Language Model Language Model Hidden Markov Model Model Stealing
SecEncoder: Logs are All You Need in Security
Muhammed Fatih Bulut, Yingqi Liu, Naveed Ahmad, Maximilian Turner, Sami Ait Ouahmane, Cameron Andrews, Lloyd Greenwald
Large Language Model Language Model Training Data Security Related Log Message
DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises
Nan Xu, Xuezhe Ma
Large Language Model Full Model Large Language Mitigating Hallucination False Sense Hallucination Dataset Prompt Generated Question

November 11, 2024

SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models
Bardiya Akhbari, Manish Gawali, Nicholas A. Dronen
Large Language Model Language Model Challenge Dataset Semantic Variation Lexical Aware Grouping Network Multiset Function Semantic Robustness

Large Language Model

Papers

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset

Challenges in Guardrailing Large Language Models for Science

Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Large Language Models Can Self-Improve in Long-context Reasoning

Can adversarial attacks by large language models be attributed?

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Verbosity $\neq$ Veracity: Demystify Verbosity Compensation Behavior of Large Language Models

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

Training Data for Large Language Model

World Models: The Safety Perspective

Top-$nσ$: Not All Logits Are You Need

Direct Preference Optimization Using Sparse Feature-Level Constraints

Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations

Entropy Controllable Direct Preference Optimization

Model Stealing for Any Low-Rank Language Model

SecEncoder: Logs are All You Need in Security

DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises

SetLexSem Challenge: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models