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 27, 2024

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding
Qing Jiang, Gen luo, Yuqin Yang, Yuda Xiong, Yihao Chen, Zhaoyang Zeng, Tianhe Ren, Lei Zhang
Large Language Model Computer Vision Human Understanding Multimodal LLM COCO Dataset
Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation
T.G.D.K. Sumanathilaka, Nicholas Micallef, Julian Hough
Large Language Model Structural Ambiguity Sense Disambiguation Quantitative Evaluation Prompt Augmentation Ambiguous Word
Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks
Zuguang Li, Shaohua Wu, Liang Li, Songge Zhang
Large Language Model Edge Network Edge Server
Break the ID-Language Barrier: An Adaption Framework for Sequential Recommendation
Xiaohan Yu, Li Zhang, Xin Zhao, Yue Wang
Large Language Model Effective Recommendation Sequential Recommendation Sequential Information Recommendation Accuracy Language Barrier BREAK for Make
Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs
Samuele Pasini, Jinhan Kim, Tommaso Aiello, Rocio Cabrera Lozoya, Antonino Sabetta, Paolo Tonella
Large Language Model Native Robustness Retrieval Augmented Generation Attack Detection Injection Attack
SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment
Jie Wang, Yichen Wang, Zhilin Zhang, Jianhao Zeng, Kaidi Wang, Zhiyang Chen
Large Language Model Emotion Embeddings Fine Grained Sentiment Fine Grained Emotion Structured Sentiment Analysis Text Based Environment
A survey on cutting-edge relation extraction techniques based on language models
Jose A. Diaz-Garcia, Julio Amador Diaz Lopez
Large Language Model Language Model Natural Language Processing Timely Survey Relation Extraction Computational Linguistics Shot Relation Extraction
Training and Evaluating Language Models with Template-based Data Generation
Yifan Zhang
Large Language Model Language Model Training Data Faithful Generation MATH Dataset GLOBEM Dataset Semantic Template
DRS: Deep Question Reformulation With Structured Output
Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang
Large Language Model Zero Shot Question Answering Open Source Large Language Model Structured Output Question Reformulation
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
Xiaoxuan Li, Yao Liu, Ruoyu Wang, Lina Yao
Large Language Model Causal Discovery Scientific Discovery Causal Event Cause Effect

November 26, 2024

Can LLMs plan paths in the real world?
Wanyi Chen, Meng-Wen Su, Nafisa Mehjabin, Mary L. Cummings
Large Language Model Real World Path Planning Navigation System
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu
Large Language Model K TOKEN Structure Learning Character Understanding Easy to Learn Token
Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting
Liyun Zhang, Dian Ding, Yu Lu, Yi-Chao Chen, Guangtao Xue
Large Language Model Language Model Medical LLM Text Modality Continuum Limit Attention Weight Emotion Class
MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation
Harsh Singh, Rocktim Jyoti Das, Mingfei Han, Preslav Nakov, Ivan Laptev
Large Language Model Zero Shot LLM Based Strategic Manipulation Adaptive Planning
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtárik, Dan Alistarh
Large Language Model Continuum Limit Reverse Graph Linearization Data Free Quantization Non Uniform Quantization
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
Pengfei Cao, Yuheng Chen, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao
Large Language Model Human Mind Single Neuron Level Knowledge Editing Language Agnostic Knowledge Neuron Polyglot File
The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations
Theodora Worledge, Tatsunori Hashimoto, Carlos Guestrin
Large Language Model Data Provenance LLM Generation Source Text Multiple Citation Domain Specific LLM
Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach
Changgeon Ko, Jisu Shin, Hoyun Song, Jeongyeon Seo, Jong C. Park
Large Language Model Model Bias Bias Evaluation Potential Bias LLM Bias
Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning
Milena Chadimová, Eduard Jurášek, Tomáš Kliegr
Large Language Model Word List Logical Reasoning Statistical Learning Cognitive Bias LLM Model LLM Prompt Input Representation Bias Reduction Rating Meaningfulness
Using Large Language Models for Expert Prior Elicitation in Predictive Modelling
Alexander Capstick, Rahul G. Krishnan, Payam Barnaghi
Large Language Model Language Model Prior Distribution Eliciting Knowledge

Large Language Model

Papers

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation

Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks

Break the ID-Language Barrier: An Adaption Framework for Sequential Recommendation

Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs

SentiXRL: An advanced large language Model Framework for Multilingual Fine-Grained Emotion Classification in Complex Text Environment

A survey on cutting-edge relation extraction techniques based on language models

Training and Evaluating Language Models with Template-based Data Generation

DRS: Deep Question Reformulation With Structured Output

Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery

Can LLMs plan paths in the real world?

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning

Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting

MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models

The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations

Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach

Meaningless is better: hashing bias-inducing words in LLM prompts improves performance in logical reasoning and statistical learning

Using Large Language Models for Expert Prior Elicitation in Predictive Modelling