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 16, 2024

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
Jingming Zhuo, Songyang Zhang, Xinyu Fang, Haodong Duan, Dahua Lin, Kai Chen
Large Language Model
Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models
Amin Abolghasemi, Leif Azzopardi, Seyyed Hadi Hashemi, Maarten de Rijke, Suzan Verberne
Large Language Model Full Model Global Evaluation Implicit Bias Document Intelligence Human Writer Attribution Quality
HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims
Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, Kunwoo Park
Large Language Model Fact Checking Verification Task Evidence Retrieval Real World Claim Herding Algorithm Veracity Prediction Open Large Language Model
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
Qinfeng Li, Yangfan Xie, Tianyu Du, Zhiqiang Shen, Zhenghan Qin, Hao Peng, Xinkui Zhao, Xianwei Zhu, Jianwei Yin, Xuhong Zhang
Large Language Model Full Model Capability Evolution Edge Deployment Model Protection Proprietary Large Language Model
Understanding the Role of LLMs in Multimodal Evaluation Benchmarks
Botian Jiang, Lei Li, Xiaonan Li, Zhaowei Li, Xiachong Feng, Lingpeng Kong, Qi Liu, Xipeng Qiu
Large Language Model Medical LLM Multimodal Large Language Model Integral Role Multimodal Reasoning Multimodal Benchmark MLLM Training
Neuron-based Personality Trait Induction in Large Language Models
Jia Deng, Tianyi Tang, Yanbin Yin, Wenhao Yang, Wayne Xin Zhao, Ji-Rong Wen
Large Language Model Personality Classification Personality Perception Trait Estimation
UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification
Jiacheng Cai, Jiahao Yu, Yangguang Shao, Yuhang Wu, Xinyu Xing
Large Language Model Medical LLM Person Identification Fingerprinting Lemma
Open Domain Question Answering with Conflicting Contexts
Siyi Liu, Qiang Ning, Kishaloy Halder, Wei Xiao, Zheng Qi, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth
Large Language Model Question Answering Context Information Open Domain Question
Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
Weixuan Wang, Jingyuan Yang, Wei Peng
Large Language Model X Vector Steering Technique Adaptive Intervention Contrastive Pair
An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
Junjie Chen, Weihang Su, Zhumin Chu, Haitao Li, Qinyao Ai, Yiqun Liu, Min Zhang, Shaoping Ma
Large Language Model Human Language Dialogue Generation Peer Review Evaluation Method Generation Benchmark
CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity
Jintao Liu, Ruixue Ding, Linhao Zhang, Pengjun Xie, Fie Huang
Large Language Model Retrieval Augmented Generation Retrieval Performance Data Diversity
EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference
Yulei Qian, Fengcun Li, Xiangyang Ji, Xiaoyu Zhao, Jianchao Tan, Kefeng Zhang, Xunliang Cai
Large Language Model Mixture of Expert Efficient Pipeline Parallel Inference Inference Optimization
Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
Yuyang Chen, Kaiyan Zhao, Yiming Wang, Ming Yang, Jian Zhang, Xiaoguang Niu
Large Language Model Code Generation Transformer Based Model Full Potential Experience Replay Transformer Based Large Language Model Code Generation Task Code Model
On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation
Xiaonan Jing, Srinivas Billa, Danny Godbout
Large Language Model Global Evaluation Language Generation Natural Language Inference Visual Analogue Scale Natural Language Generation Faithfulness Test
Negative-Prompt-driven Alignment for Generative Language Model
Shiqi Qiao, Ning Xv, Biao Liu, Xin Geng
Large Language Model Language Model Generative Language Model Alignment Dataset Negative Prompt Prompt Alignment
DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs
Yingsong Luo, Ling Chen
Large Language Model Balancing Weight Dense Environment Weight Only Quantization Quantization Parameter
Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish
Juan Manuel Pérez, Paula Miguel, Viviana Cotik
Large Language Model Language Model Hate Speech Hate Speech Detection Continuous Spanish
Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval
Hai-Long Nguyen, Tan-Minh Nguyen, Duc-Minh Nguyen, Thi-Hai-Yen Vuong, Ha-Thanh Nguyen, Xuan-Hieu Phan
Large Language Model Reasoning Capability Implicit Knowledge Logical Reasoning Capability Legal Retrieval
SoK: Prompt Hacking of Large Language Models
Baha Rababah, Shang (Tommy)Wu, Matthew Kwiatkowski, Carson Leung, Cuneyt Gurcan Akcora
Large Language Model Style PROMPT Prompt Attack LLM Integrated Application
Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning
Huiwen Wu, Xiaohan Li, Xiaogang Xu, Jiafei Wu, Deyi Zhang, Zhe Liu
Large Language Model Contrastive Learning LLM Inference Layer Representation DIII D Tokamak

Large Language Model

Papers

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models

HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Understanding the Role of LLMs in Multimodal Evaluation Benchmarks

Neuron-based Personality Trait Induction in Large Language Models

UTF:Undertrained Tokens as Fingerprints A Novel Approach to LLM Identification

Open Domain Question Answering with Conflicting Contexts

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors

An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation

CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay

On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation

Negative-Prompt-driven Alignment for Generative Language Model

DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs

Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish

Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval

SoK: Prompt Hacking of Large Language Models

Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning