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 4, 2024

Thinking Forward and Backward: Effective Backward Planning with Large Language Models
Allen Z. Ren, Brian Ichter, Anirudha Majumdar
Large Language Model Language Model Planning Domain Future Perspective Forward Pas
Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education
Alexandra Vassar, Jake Renzella, Emily Ross, Andrew Taylor
Large Language Model Fine Tuning LLM Based Supervised Fine Tuning Education Domain Digital Computing Online Discourse Pedagogical Alignment
RAGViz: Diagnose and Visualize Retrieval-Augmented Generation
Tevin Wang, Jingyuan He, Chenyan Xiong
Large Language Model Retrieval Augmented Generation Faithful Generation Medical Diagnosis LLM Inference Answer Generation Attention Visualization
DynaSaur: Large Language Agents Beyond Predefined Actions
Dang Nguyen, Viet Dac Lai, Seunghyun Yoon, Ryan A. Rossi, Handong Zhao, Ruiyi Zhang, Puneet Mathur, Nedim Lipka, Yu Wang, Trung Bui, Franck Dernoncourt, Tianyi Zhou
Large Language Model LLM Based LLM Agent Past Action Narrow Environment Agent Framework

November 3, 2024

Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups
Răzvan-Alexandru Smădu, David-Gabriel Ion, Dumitru-Clementin Cercel, Florin Pop, Mihaela-Claudia Cercel
Large Language Model Natural Language Multi Domain Multiword Expression Lexical Complexity
Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
Yuefeng Peng, Junda Wang, Hong Yu, Amir Houmansadr
Large Language Model Retrieval Augmented Generation Backdoor Attack Document Level Information Extraction Data Extraction Attack
An Exploration of Higher Education Course Evaluation by Large Language Models
Bo Yuan, Jiazi Hu
Large Language Model Full Model Environment Exploration Large Language Course Evaluation
Graph-based Confidence Calibration for Large Language Models
Yukun Li, Sijia Wang, Lifu Huang, Li-Ping Liu
Large Language Model Confidence Calibration Calibrated Confidence Correctness Check Confidence Estimate
Ontology Population using LLMs
Sanaz Saki Norouzi, Adrita Barua, Antrea Christou, Nikita Gautam, Andrew Eells, Pascal Hitzler, Cogan Shimizu
Large Language Model Knowledge Graph Natural Language Language Understanding
Large Language Model Supply Chain: Open Problems From the Security Perspective
Qiang Hu, Xiaofei Xie, Sen Chen, Lei Ma
Large Language Model Visual Perspective Security Related Open Problem
Are LLMs good pragmatic speakers?
Mingyue Jian, Siddharth Narayanaswamy
Large Language Model Referring Expression Pragmatic Reasoning Linguistic Pragmatic Pragmatic Speaker
Enhancing LLM Evaluations: The Garbling Trick
William F. Bradley
Large Language Model Reasoning Capability LLM Evaluation Arithmetic Circuit
High-performance automated abstract screening with large language model ensembles
Rohan Sanghera, Arun James Thirunavukarasu, Marc El Khoury, Jessica O'Logbon, Yuqing Chen, Archie Watt, Mustafa Mahmood, Hamid Butt, George Nishimura, Andrew Soltan
Large Language Model Diverse Ensemble Systematic Review High Performance LLM Prompt Abstract Text Large Scale Screening
Sample-Efficient Alignment for LLMs
Zichen Liu, Changyu Chen, Chao Du, Wee Sun Lee, Min Lin
Large Language Model Preference Learning LLM Alignment Online Alignment
EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark
Ming Li, Jike Zhong, Tianle Chen, Yuxiang Lai, Konstantinos Psounis
Large Language Model Large Multimodal Model Multimodal Benchmark Closed Source Large Language Model
A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?
QiHong Chen, Jiawei Li, Jiecheng Deng, Jiachen Yu, Justin Tian Jin Chen, Iftekhar Ahmed
Large Language Model Code Generation Real World Code LLM Generated Code Deep Dive

November 2, 2024

Interacting Large Language Model Agents. Interpretable Models and Social Learning
Adit Jain, Vikram Krishnamurthy
Large Language Model LeArning Abstract Interpretable Model Social Learning Agent Model Bounded Rational Bayesian Agent
Diversidade linguística e inclusão digital: desafios para uma ia brasileira
Raquel Meister Ko Freitag
Large Language Model Generative AI Linguistic Diversity Brazilian Portuguese Selection Bias Computational Sociolinguistics Language Clustering
PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment
Dongxu Liu, Bing Xu, Yinzhuo Chen, Bufan Xu, Wenpeng Lu, Muyun Yang, Tiejun Zhao
Large Language Model Reinforcement Learning Human Preference Preference Alignment LLM Alignment Preference Representation Preference Modeling
Transfer Learning for Finetuning Large Language Models
Tobias Strangmann, Lennart Purucker, Jörg K.H. Franke, Ivo Rapant, Fabio Ferreira, Frank Hutter
Large Language Model Transfer Learning Meta Training Meta Optimization

Large Language Model

Papers

Thinking Forward and Backward: Effective Backward Planning with Large Language Models

Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education

RAGViz: Diagnose and Visualize Retrieval-Augmented Generation

DynaSaur: Large Language Agents Beyond Predefined Actions

Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors

An Exploration of Higher Education Course Evaluation by Large Language Models

Graph-based Confidence Calibration for Large Language Models

Ontology Population using LLMs

Large Language Model Supply Chain: Open Problems From the Security Perspective

Are LLMs good pragmatic speakers?

Enhancing LLM Evaluations: The Garbling Trick

High-performance automated abstract screening with large language model ensembles

Sample-Efficient Alignment for LLMs

EEE-Bench: A Comprehensive Multimodal Electrical And Electronics Engineering Benchmark

A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?

Interacting Large Language Model Agents. Interpretable Models and Social Learning

Diversidade linguística e inclusão digital: desafios para uma ia brasileira

PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment

Transfer Learning for Finetuning Large Language Models