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 26, 2024

APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents
Jun Yu Chen, Tao Gao
Large Language Model Autonomous Agent Open World Architecture Design Construction Industry Diverse Platform Spatial Reasoning
Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems
Lorraine Vanel, Ariel R. Ramos Vela, Alya Yacoubi, Chloé Clavel (IDS, S2A, LTCI)
Large Language Model Response Generation Conversational System Human Evaluation Protocol Affective Tutoring System
Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness
Avinash Amballa, Durga Sandeep Saluru, Gayathri Akkinapalli, Abhishek Sureddy, Akshay Kumar Sureddy
Large Language Model Language Model Full Model Alignment Problem Human SAFETY Unsafe Prompt Helpfulness Score Multi Attribute Helpfulness Dataset

November 25, 2024

Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models
Yao Fu, Yin Yu, Xiaotian Han, Runchao Li, Xianxuan Long, Haotian Yu, Pan Li
Large Language Model Language Model Knowledge Distillation Fine Tuning Self Distillation Mini Batch Large Lm Parallel Self Distillation
Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)
Tim Hartill
Large Language Model Yes No Question Reasoning System Larger Language Model Smaller Language Model Context Dependent Question Electronic Thesis Free Text Rationale Unseen Composition
Towards Agentic Schema Refinement
Agapi Rissaki, Ilias Fountalis, Nikolaos Vasiloglou, Wolfgang Gatterbauer
Large Language Model Large Scale New Database Schema Graph
Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings
Carolin M. Schuster, Maria-Alexandra Dinisor, Shashwat Ghatiwala, Georg Groh
Large Language Model Jina Embeddings Gender Bias Stereotype Content Bias Challenge Contextualised Word
DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model
Hong Cai Chen, Longchang Wu, Ming Gao, Lingrui Shen, Jiarui Zhong, Yipin Xu
Large Language Model Document Relevance Automatic Extraction Electronic Design Automation Analog Circuit Parameter Space Reconstruction
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
Xiaocong Yang, Jiacheng Lin, Ziqi Wang, Chengxiang Zhai
Large Language Model LeArning Abstract Complex Reasoning Computational Approach Math Word Problem Graph Search Reasoning Challenge
Blockchain Meets LLMs: A Living Survey on Bidirectional Integration
Jianghao Gong, Peiqi Yan, Yue Zhang, Hongli An, Logan Liu
Large Language Model Medical LLM Multimodal Large Language Model Blockchain Based Platform Large Language Research Survey Bidirectional Generation
FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web
Cheng-Wei Lin, Wan-Hsuan Hsieh, Kai-Xin Guan, Chan-Jan Hsu, Chia-Chen Kuo, Chuan-Lin Lai, Chung-Wei Chung, Ming-Jen Wang, Da-Shan Shiu
Large Language Model Chinese Character Automatic Curation Large Scale Chinese
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
Duo Wu, Jinghe Wang, Yuan Meng, Yanning Zhang, Le Sun, Zhi Wang
Large Language Model Partial Execution
BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
Shaolei Zhang, Kehao Zhang, Qingkai Fang, Shoutao Guo, Yan Zhou, Xiaodong Liu, Yang Feng
Large Language Model Alignment Problem Multilingual Large Language Model High Resource Language Complex Instruction Multilingual Capability Code Efficiency
Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures
Fu-Chieh Chang, Pei-Yuan Wu
Large Language Model Complex Reasoning Integral Role Chain of Thought Simple Structure Arithmetic Task
NormXLogit: The Head-on-Top Never Lies
Sina Abbasi, Mohammad Reza Modarres, Mohammad Taher Pilehvar
Large Language Model Inherent Interpretability Transformer Architecture Word Embeddings Level Explanation
What can LLM tell us about cities?
Zhuoheng Li, Yaochen Wang, Zhixue Song, Yuqi Huang, Rui Bao, Guanjie Zheng, Zhenhui Jessie Li
Large Language Model Machine Learning Model Medical LLM Data Driven Urban Environment
Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models
Hao Yi, Qingyang Li, Yulan Hu, Fuzheng Zhang, Di Zhang, Yong Liu
Large Language Model Video Text AI Feedback Reference Dataset VQA Datasets Iterative Preference Learning
Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains
Arion Das, Asutosh Mishra, Amitesh Patel, Soumilya De, V. Gurucharan, Kripabandhu Ghosh
Large Language Model Case Study High Explainability Human Reasoning Self Information Interpretable Algorithm High Risk Domain
LLM Augmentations to support Analytical Reasoning over Multiple Documents
Raquib Bin Yousuf, Nicholas Defelice, Mandar Sharma, Shengzhe Xu, Naren Ramakrishnan
Large Language Model Logical Reasoning Document Relevance LLM Based Augmentation Intelligence Community
LLMPirate: LLMs for Black-box Hardware IP Piracy
Vasudev Gohil, Matthew DeLorenzo, Veera Vishwa Achuta Sai Venkat Nallam, Joey See, Jeyavijayan Rajendran
Large Language Model Logic Design

Large Language Model

Papers

APT: Architectural Planning and Text-to-Blueprint Construction Using Large Language Models for Open-World Agents

Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systems

Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness

Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models

Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)

Towards Agentic Schema Refinement

Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings

DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

Blockchain Meets LLMs: A Living Survey on Bidirectional Integration

FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Web

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures

NormXLogit: The Head-on-Top Never Lies

What can LLM tell us about cities?

Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models

Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains

LLM Augmentations to support Analytical Reasoning over Multiple Documents

LLMPirate: LLMs for Black-box Hardware IP Piracy