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

December 16, 2024

Stepwise Reasoning Error Disruption Attack of LLMs
Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu
Large Language Model Reasoning Task Reasoning Process Reasoning Error
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Qi Ye, Zhicheng Dou
Large Language Model Retrieval Augmented Generation Faithful Generation Evidence Piece Evidence Collection
A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection
Simon Hachmeier, Robert Jäschke
Large Language Model Language Model New Benchmark Robustness Analysis Entity Information Entity Discovery
Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimation
Leonidas Zotos, Hedderik van Rijn, Malvina Nissim
Large Language Model Greater Public Use Model Uncertainty Difficulty Prediction
QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs
Mohammad Aflah Khan, Neemesh Yadav, Sarah Masud, Md. Shad Akhtar
Large Language Model Complex Reasoning Multiple Choice Rationale Generation Indian English
Personalized LLM for Generating Customized Responses to the Same Query from Different Users
Hang Zeng, Chaoyue Niu, Fan Wu, Chengfei Lv, Guihai Chen
Large Language Model Response Generation Multi User Question Representation
C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness
Yu Kang, Xianghui Sun, Liangyu Chen, Wei Zou
Large Language Model Chain of Thought Reasoning Capability Reasoning Step
QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models
Changhai Zhou, Yuhua Zhou, Shijie Han, Qian Qiao, Hongguang Li
Large Language Model Natural Language Processing Structured Pruning Accurate Quantization
EvoLlama: Enhancing LLMs' Understanding of Proteins via Multimodal Structure and Sequence Representations
Nuowei Liu, Changzhi Sun, Tao Ji, Junfeng Tian, Jianxin Tang, Yuanbin Wu, Man Lan
Large Language Model Human Understanding Non Structural Protein Protein Sequence Encoder Sequence Representation Protein Language Domain Specific Instruction
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Yuchen Fu, Zifeng Cheng, Zhiwei Jiang, Zhonghui Wang, Yafeng Yin, Zhengliang Li, Qing Gu
Large Language Model Jina Embeddings Sentence Embeddings Style PROMPT Training Free Diverse Prompt
Let your LLM generate a few tokens and you will reduce the need for retrieval
Hervé Déjean
Large Language Model App to App Retrieval Classification Task Community Need Thinking Token Augmented Generation Answer Token
DART: An AIGT Detector using AMR of Rephrased Text
Hyeonchu Park, Byungjun Kim, Bugeun Kim
Large Language Model Text Modality Semantic Parsing Human Like AI Generated Text Detection Syntactic Feature
Embodied CoT Distillation From LLM To Off-the-shelf Agents
Wonje Choi, Woo Kyung Kim, Minjong Yoo, Honguk Woo
Large Language Model Language Model Medical LLM Embodied Vision Embodied Task
FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
Zekai Li, Jintu Zheng, Ji Liu, Han Liu, Haowei Zhu, Zeping Li, Fuwei Yang, Haiduo Huang, Jinzhang Peng, Dong Li, Lu Tian, Emad Barsoum
Large Language Model Token Pruning Model Inference Token Sparsification Fine Grained Token Token Routing
Understanding Knowledge Hijack Mechanism in In-context Learning through Associative Memory
Shuo Wang, Issei Sato
Large Language Model Context Learning Poisoning Attack Different Context Next Token Prediction Associative Memory Layer Transformer Token Prediction
Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models
Zaifu Zhan, Rui Zhang
Large Language Model New Framework Multi Task Learning Multi Task High Quality Biomedical Datasets Linear Combination Data Optimization
Are Large Language Models Useful for Time Series Data Analysis?
Francis Tang, Ying Ding
Large Language Model Autoregressive Model Time Series Data Time Series Analysis
INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models
Aum Kendapadi, Kerem Zaman, Rakesh R. Menon, Shashank Srivastava
Large Language Model Language Model Teacher Student Interactive Learning Digital Action Curiosity Driven Learning
How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach
Abdulrahman Althobaiti, Angel Ayala, JingYing Gao, Ali Almutairi, Mohammad Deghat, Imran Razzak, Francisco Cruz
Large Language Model Knowledge Graph Robotics Domain Natural Language Instruction Robot Action Robot Safety Safety Verification Learning Approach Safety Layer
FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation
Dannong Wang, Daniel Kim, Bo Jin, Xingjian Zhao, Tianfan Fu, Steve Yang, Xiao-Yang Liu
Large Language Model Adaptation Concern Low Rank Input Sequence

Large Language Model

Papers

Stepwise Reasoning Error Disruption Attack of LLMs

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection

Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimation

QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs

Personalized LLM for Generating Customized Responses to the Same Query from Different Users

C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness

QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models

EvoLlama: Enhancing LLMs' Understanding of Proteins via Multimodal Structure and Sequence Representations

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Let your LLM generate a few tokens and you will reduce the need for retrieval

DART: An AIGT Detector using AMR of Rephrased Text

Embodied CoT Distillation From LLM To Off-the-shelf Agents

FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing

Understanding Knowledge Hijack Mechanism in In-context Learning through Associative Memory

Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models

Are Large Language Models Useful for Time Series Data Analysis?

INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models

How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach

FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation