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 3, 2024

Strong Preferences Affect the Robustness of Value Alignment
Ziwei Xu, Mohan Kankanhalli
Large Language Model Native Robustness Human Preference Value Alignment Preference Model
Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
Mingyang Wang, Lukas Lange, Heike Adel, Jannik Strötgen, Hinrich Schütze
Large Language Model Language Model Model Editing
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Xiang Wang, Xiangnan He, Tat-seng Chua
Large Language Model Language Model Knowledge Editing Null Space Edit Operation
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection
Tianxiang Chen, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Jieping Ye, Nenghai Yu
Large Language Model Parameter Efficient Fine Tuning Pre Trained Large Language Model Efficient Deep Knowledge Injection LLaMA 3 Shallow Layer
Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models
Rui Meng, Ye Liu, Lifu Tu, Daqing He, Yingbo Zhou, Semih Yavuz
Large Language Model Natural Language Instruction Human Annotated Urban Traffic Traffic Light Semantic Processing Word Semantics
Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
Yuxuan Yao, Han Wu, Mingyang Liu, Sichun Luo, Xiongwei Han, Jie Liu, Zhijiang Guo, Linqi Song
Large Language Model Model Performance Model Selection Community Need Alignment Performance
Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach
Wanyi Liu, Long Chen, Zhenzhou Tang
Large Language Model Evolutionary Algorithm Multi Objective Optimization Global Optimization Multi Objective Evolutionary Algorithm Evolutionary Operator
Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
Guobin Shen, Dongcheng Zhao, Yiting Dong, Xiang He, Yi Zeng
Large Language Model Jailbreak Attack Safety Fine Tuning
CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning
Huimu Yu, Xing Wu, Weidong Yin, Debing Zhang, Songlin Hu
Large Language Model Preference Learning Code Mixed Reasoning Performance Preference Modeling
Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang, Chenyu You, Muchao Ye, Zhaohan Xi
Large Language Model LLM Inference Data Curation Prompt Customization Real Time Customization Defense Framework
CaLMFlow: Volterra Flow Matching using Causal Language Models
Sizhuang He, Daniel Levine, Ivan Vrkic, Marco Francesco Bressana, David Zhang, Syed Asad Rizvi, Yangtian Zhang, Emanuele Zappala, David van Dijk
Large Language Model Flow Matching Language Modeling Causal Language Conditional Flow Matching
Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference
Wei Cheng, Tianlu Wang, Yanmin Ji, Fan Yang, Keren Tan, Yiyu Zheng
Large Language Model Context Learning Calibration Performance Label Free Discriminative Reply Calibrated Prediction
Efficiently Deploying LLMs with Controlled Risk
Michael J. Zellinger, Matt Thomson
Large Language Model Medical LLM Training Free Hierarchical Structure Abstention Ability Intrinsic Uncertainty
ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
Xiangyu Peng, Congying Xia, Xinyi Yang, Caiming Xiong, Chien-Sheng Wu, Chen Xing
Large Language Model Reasoning Path Self Improvement Reasoning Trajectory

October 2, 2024

A Watermark for Black-Box Language Models
Dara Bahri, John Wieting, Dana Alon, Donald Metzler
Large Language Model Agnostic Watermarking Next Token Prediction Black Box Language Model Watermarking Scheme
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
Jonas Gehring, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, Gabriel Synnaeve
Large Language Model Reinforcement Learning End to End Code Synthesis Competitive Programming Execution Based
Precision Knowledge Editing: Enhancing Safety in Large Language Models
Xuying Li, Zhuo Li, Yuji Kosuga, Yasuhiro Yoshida, Victor Bian
Large Language Model Human SAFETY Knowledge Editing Knowledge Editing Method Toxicity Detection Datasets
Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions
Qian Ruan, Ilia Kuznetsov, Iryna Gurevych
Large Language Model Text Generation Study Feature Intent Classification Self Driven Revision
FLAG: Financial Long Document Classification via AMR-based GNN
Bolun "Namir" Xia, Aparna Gupta, Mohammed J. Zaki
Large Language Model LLM Embeddings Financial Text Label Aggregation Long Document Classification Abstract Meaning Representation Graph
LLM+KG@VLDB'24 Workshop Summary
Arijit Khan, Tianxing Wu, Xi Chen
Large Language Model Knowledge Graph Data Challenge Workshop Report

Large Language Model

Papers

Strong Preferences Affect the Robustness of Value Alignment

Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection

Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models

Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling

Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach

Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models

CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning

Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation

CaLMFlow: Volterra Flow Matching using Causal Language Models

Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference

Efficiently Deploying LLMs with Controlled Risk

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

A Watermark for Black-Box Language Models

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Precision Knowledge Editing: Enhancing Safety in Large Language Models

Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions

FLAG: Financial Long Document Classification via AMR-based GNN

LLM+KG@VLDB'24 Workshop Summary