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 4, 2024

Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms
Haoran Yin, Anna V. Kononova, Thomas Bäck, Niki van Stein
Large Language Model High Efficiency Practical Algorithm Specie Evolution Evolutionary Computation Single Point Mutation Adaptive Mutation
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
Yiwu Zhong, Zhuoming Liu, Yin Li, Liwei Wang
Large Language Model Edge Pruning Multi Modal Large Language Model Aim 2 Token Merging Adaptive Inference
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
Sravanti Addepalli, Yerram Varun, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain
Large Language Model Adversarial Attack Complex Prompt Adversarial Prompt Visual Naturalness
Linq-Embed-Mistral Technical Report
Chanyeol Choi, Junseong Kim, Seolhwa Lee, Jihoon Kwon, Sangmo Gu, Yejin Kim, Minkyung Cho, Jy-yong Sohn
Large Language Model Retrieval Performance Retrieval Task
Automatic detection of diseases in Spanish clinical notes combining medical language models and ontologies
Leon-Paul Schaub Torre, Pelayo Quiros, Helena Garcia Mieres
Large Language Model Top Level Ontology Automatic Detection Common Disease Medical Text BiOmedical Ontology
Byte BPE Tokenization as an Inverse string Homomorphism
Saibo Geng, Sankalp Gambhir, Chris Wendler, Robert West
Large Language Model Neural Architecture
Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media
Kun Li, Chenwei Dai, Wei Zhou, Songlin Hu
Large Language Model Language Model Fine Grained Social Medium Human Behavior
Unifying KV Cache Compression for Large Language Models with LeanKV
Yanqi Zhang, Yuwei Hu, Runyuan Zhao, John C.S. Lui, Haibo Chen
Large Language Model Key Value Cache Key Value Cache Compression
ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning
Zhe Xie, Zeyan Li, Xiao He, Longlong Xu, Xidao Wen, Tieying Zhang, Jianjun Chen, Rui Shi, Dan Pei
Large Language Model Synthetic Data Time Series Complex Reasoning Human Understanding Synthetic Time Series Time Series Alignment
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
Peiyan Zhang, Haibo Jin, Leyang Hu, Xinnuo Li, Liying Kang, Man Luo, Yangqiu Song, Haohan Wang
Large Language Model Optimization Purpose Text Modality AI System Prompt Optimization Code Optimization Optimization Performance Response Curve
CBEval: A framework for evaluating and interpreting cognitive biases in LLMs
Ammar Shaikh, Raj Abhijit Dandekar, Sreedath Panat, Rajat Dandekar
Large Language Model Language Model New Framework Cognitive Bias
Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models
Sergio E. Zanotto, Segun Aroyehun
Large Language Model Natural Language Strong Consistency Text Based Linguistic Feature Human Written Text Linguistic Analysis High Diagram to Diagram Variability
Curriculum-style Data Augmentation for LLM-based Metaphor Detection
Kaidi Jia, Yanxia Wu, Rongsheng Li
Large Language Model Data Augmentation Closed Source Large Language Model Metaphor Detection

December 3, 2024

Enhancing Trust in Large Language Models with Uncertainty-Aware Fine-Tuning
Ranganath Krishnan, Piyush Khanna, Omesh Tickoo
Large Language Model Fine Tuning Language Generation Causal Language Building Trust Calibrated Uncertainty
Removing Spurious Correlation from Neural Network Interpretations
Milad Fotouhi, Mohammad Taha Bahadori, Oluwaseyi Feyisetan, Payman Arabshahi, David Heckerman
Large Language Model Spurious Correlation Text Based Confounders Causal Mediation Analysis Co Localization
Measuring Bias of Web-filtered Text Datasets and Bias Propagation Through Training
Youssef Mansour, Reinhard Heckel
Large Language Model Neural Network Data Set Training Data Text Datasets Computer Vision Datasets Classification Datasets Quantifying Bias
Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model
María Victoria Carro
Large Language Model Global Impact Reinforcement Learning From Human Feedback User Trust Deceptive Diffusion Visual Sycophancy
An Evolutionary Large Language Model for Hallucination Mitigation
Abdennour Boulesnane, Abdelhakim Souilah
Large Language Model Question Answering Question Answer Pair Mitigating Hallucination Human Labeled
Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training
H. Toprak Kesgin, M. Kaan Yuce, Eren Dogan, M. Egemen Uzun, Atahan Uz, Elif Ince, Yusuf Erdem, Osama Shbib, Ahmed Zeer, M. Fatih Amasyali
Large Language Model Language Model Training Data Large Corpus Multilingual Model New Method Corpus Level
Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek
Ahmed Zeer, Eren Dogan, Yusuf Erdem, Elif Ince, Osama Shbib, M. Egemen Uzun, Atahan Uz, M. Kaan Yuce, H. Toprak Kesgin, M. Fatih Amasyali
Large Language Model Model Performance Model Architecture

Large Language Model

Papers

Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

Linq-Embed-Mistral Technical Report

Automatic detection of diseases in Spanish clinical notes combining medical language models and ontologies

Byte BPE Tokenization as an Inverse string Homomorphism

Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media

Unifying KV Cache Compression for Large Language Models with LeanKV

ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning

Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization

CBEval: A framework for evaluating and interpreting cognitive biases in LLMs

Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models

Curriculum-style Data Augmentation for LLM-based Metaphor Detection

Enhancing Trust in Large Language Models with Uncertainty-Aware Fine-Tuning

Removing Spurious Correlation from Neural Network Interpretations

Measuring Bias of Web-filtered Text Datasets and Bias Propagation Through Training

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

An Evolutionary Large Language Model for Hallucination Mitigation

Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training

Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek