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 29, 2024

TQA-Bench: Evaluating LLMs for Multi-Table Question Answering with Scalable Context and Symbolic Extension
Zipeng Qiu, You Peng, Guangxin He, Binhang Yuan, Chen Wang
Large Language Model Question Answering Context Length MT Bench Symbolic Computation Table Question Answering Table Question
A Simple and Provable Scaling Law for the Test-Time Compute of Large Language Models
Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou
Large Language Model Language Model Scaling Law Two Stage Black Box LLM
Towards Understanding Retrieval Accuracy and Prompt Quality in RAG Systems
Shengming Zhao, Yuheng Huang, Jiayang Song, Zhijie Wang, Chengcheng Wan, Lei Ma
Large Language Model Retrieval Augmented Generation System Description Retrieval Performance Imperfect Recall
Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
Yujin Han, Lei Xu, Sirui Chen, Difan Zou, Chaochao Lu
Large Language Model Critique Ability Object Surface Knowledge Comprehension Capability

November 28, 2024

On the effectiveness of discrete representations in sparse mixture of experts
Giang Do, Kha Pham, Hung Le, Truyen Tran
Large Language Model Expert Knowledge Vector Quantization Discrete Representation Sparse Mixture
Marconi: Prefix Caching for the Era of Hybrid LLMs
Rui Pan, Zhuang Wang, Zhen Jia, Can Karakus, Luca Zancato, Tri Dao, Ravi Netravali, Yida Wang
Large Language Model Memory Trace New Era Language Modeling Novel RF Editing Pipeline Recurrent Layer Forward Caching
OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation
Se-eun Yoon, Xiaokai Wei, Yexi Jiang, Rachit Pareek, Frank Ong, Kevin Gao, Julian McAuley, Michelle Gong
Large Language Model Effective Recommendation Easy Tool Recommendation Diversity Synthetic Query Indirect Request
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
Akhiad Bercovich, Tomer Ronen, Talor Abramovich, Nir Ailon, Nave Assaf, Mohammad Dabbah, Ido Galil, Amnon Geifman, Yonatan Geifman, Izhak Golan, Netanel Haber, Ehud Karpas, Itay Levy, Shahar Mor, Zach Moshe, Najeeb Nabwani, Omri Puny, Ran Rubin, Itamar Schen, Ido Shahaf, Oren Tropp, Omer Ullman Argov, Ran Zilberstein, Ran El-Yaniv
Large Language Model LLM Inference Language Modeling Large Language Model Inference Puzzle Solving Inference Performance SEMI SuperYOLO Na
Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures
Yicheng Zhang, Zhen Qin, Zhaomin Wu, Shuiguang Deng
Large Language Model Fine Tuning Data Driven Heterogeneous Model
CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients
Shengjun Zhu (1), Siyu Liu (2), Yang Li (3), Qing Lei, Hongyan Hou, Hewei Jiang, Shujuan Guo, Feng Wang, Rongshang Chen, Xionglin Fan, Shengce Tao, Jiaxin Cai ((1) School of Mathematics and Statistics, Xiamen University of Technology, Xiamen, China, (2) School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China, (3) Shanghai Center for Systems Biomedicine, Key Laboratory of Systems Biomedicine (Ministry of Education), Shanghai Jiao Tong University, Shanghai, China)
Large Language Model Multi Objective Imputation Algorithm Missing Value Coronavirus Disease 2019 Disease Severity Clinical Outcome
Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph
Yutong Zhang, Lixing Chen, Shenghong Li, Nan Cao, Yang Shi, Jiaxin Ding, Zhe Qu, Pan Zhou, Yang Bai
Large Language Model Medical LLM Domain Specific Domain Knowledge Specific Knowledge Graph Expertise Level
Mars-PO: Multi-Agent Reasoning System Preference Optimization
Xiaoxuan Lou, Chaojie Wang, Bo An
Large Language Model Complex Reasoning Mathematical Reasoning Reasoning Benchmark
DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs
Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
Large Language Model Semantic Embeddings Conversational Model Personalized Dialogue Conversational Large Language Model Dynamic Inference Autoregressive LLM
Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems
Mansi Rana, Kadri Hacioglu, Sindhuja Gopalan, Maragathamani Boothalingam
Large Language Model Knowledge Distillation Dialogue System Speech Based Age Conversational Data Dialogue Flow Zero Shot Slot Filling
Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease
Junan Li, Yunxiang Li, Yuren Wang, Xixin Wu, Helen Meng
Large Language Model Language Model Alzheimer'S Disease Common Disease Embracing CompAct Dementia Detection Closing Set Effective Feature Image Attack

November 27, 2024

UOE: Unlearning One Expert Is Enough For Mixture-of-experts LLMS
Haomin Zhuang, Yihua Zhang, Kehan Guo, Jinghan Jia, Gaowen Liu, Sijia Liu, Xiangliang Zhang
Large Language Model Expert Knowledge
On the Effectiveness of Incremental Training of Large Language Models
Miles Q. Li, Benjamin C. M. Fung, Shih-Chia Huang
Large Language Model Layer Wise Continual Training Incremental Training
Cross-modal Information Flow in Multimodal Large Language Models
Zhi Zhang, Srishti Yadav, Fengze Han, Ekaterina Shutova
Large Language Model Multimodal Large Language Model Vision Language Task Multimodal Representation
LLM-ABBA: Understand time series via symbolic approximation
Erin Carson, Xinye Chen, Cheng Kang
Large Language Model Time Series Time Series Representation Numerical Approximation DaG LLM
Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding
Ziyin Zhang, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Rui Wang, Zhaopeng Tu
Large Language Model Text Generation Speculative Decoding Draft Model Self Verification

Large Language Model

Papers

TQA-Bench: Evaluating LLMs for Multi-Table Question Answering with Scalable Context and Symbolic Extension

A Simple and Provable Scaling Law for the Test-Time Compute of Large Language Models

Towards Understanding Retrieval Accuracy and Prompt Quality in RAG Systems

Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability

On the effectiveness of discrete representations in sparse mixture of experts

Marconi: Prefix Caching for the Era of Hybrid LLMs

OMuleT: Orchestrating Multiple Tools for Practicable Conversational Recommendation

Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures

CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph

Mars-PO: Multi-Agent Reasoning System Preference Optimization

DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs

Zero-shot Slot Filling in the Age of LLMs for Dialogue Systems

Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease

UOE: Unlearning One Expert Is Enough For Mixture-of-experts LLMS

On the Effectiveness of Incremental Training of Large Language Models

Cross-modal Information Flow in Multimodal Large Language Models

LLM-ABBA: Understand time series via symbolic approximation

Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding