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 7, 2024

Exploring Hierarchical Molecular Graph Representation in Multimodal LLMs
Chengxin Hu, Hao Li
Large Language Model Multimodal Large Language Model Multimodal LLM Molecular Graph Graph Feature Molecule Text Hierarchical Graph
Self-Calibrated Listwise Reranking with Large Language Models
Ruiyang Ren, Yuhao Wang, Kun Zhou, Wayne Xin Zhao, Wenjie Wang, Jing Liu, Ji-Rong Wen, Tat-Seng Chua
Large Language Model Relevance Score Document Re Ranking Listwise Rerankers
Measure-to-measure interpolation using Transformers
Borjan Geshkovski, Philippe Rigollet, Domènec Ruiz-Balet
Large Language Model Transformer Megatron Decepticons Transformer Based Head Transformer Probability Measure Interpolation Quality
Best Practices for Distilling Large Language Models into BERT for Web Search Ranking
Dezhi Ye, Junwei Hu, Jiabin Fan, Bowen Tian, Jie Liu, Haijin Liang, Jin Ma
Large Language Model Zero Shot Prompt Learning Ticket BERT Large Language Autoregressive Language Model Best Practice Text Ranking
Meta-Reasoning Improves Tool Use in Large Language Models
Lisa Alazraki, Marek Rei
Large Language Model LLM Fine Tuning Reasoning Datasets Context Demonstration Meta Reasoning Tool Usage
One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity
Sonia K. Murthy, Tomer Ullman, Jennifer Hu
Large Language Model Full Model Human Language Alignment Problem Population Level Population Diversity Conceptual Diversity
DELIFT: Data Efficient Language model Instruction Fine Tuning
Ishika Agarwal, Krishna Killamsetty, Lucian Popa, Marina Danilevksy
Large Language Model Fine Tuning Instruction Tuned Language Model Continual Fine Tuning
Bayesian Calibration of Win Rate Estimation with LLM Evaluators
Yicheng Gao, Gonghan Xu, Zhe Wang, Arman Cohan
Large Language Model Generative Language Model LLM Evaluator Probability Estimation Bayesian Calibration
Variational Low-Rank Adaptation Using IVON
Bai Cong, Nico Daheim, Yuesong Shen, Daniel Cremers, Rio Yokota, Mohammad Emtiyaz Khan, Thomas Möllenhoff
Large Language Model Adaptation Concern Large Language Variational Method Variational Learning Online Newton
Leveraging LLMs to Enable Natural Language Search on Go-to-market Platforms
Jesse Yao, Saurav Acharya, Priyaranjan Parida, Srinivas Attipalli, Ali Dasdan
Large Language Model Diverse Platform Natural Language Query Entity Retrieval
Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method
Teodora Baluta, Pascal Lamblin, Daniel Tarlow, Fabian Pedregosa, Gintare Karolina Dziugaite
Large Language Model Practical Method Distribution Data Unlearning Framework Harmful Unlearning
Benchmarking Large Language Models with Integer Sequence Generation Tasks
Daniel O'Malley, Manish Bhattarai, Javier Santos
Large Language Model New Task Input Sequence Sequence Generation Novel Benchmark Code Synthesis
Measuring short-form factuality in large language models
Jason Wei, Nguyen Karina, Hyung Won Chung, Yunxin Joy Jiao, Spencer Papay, Amelia Glaese, John Schulman, William Fedus
Large Language Model Global Evaluation GPT 4 Non Negative Textual Response Factual Claim
Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation
Vaibhav Seth, Arinjay Pathak, Ayan Sengupta, Natraj Raman, Sriram Gopalakrishnan, Tanmoy Chakraborty
Large Language Model Fine Tuning Parameter Efficient Fine Tuning Adaptation Concern Bayesian Perspective Efficient Fine Tuning Reparameterization Method
CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
Jierui Li, Hung Le, Yinbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo
Large Language Model Language Model Code Generation Real World Code Tree Search Execution Based

November 6, 2024

A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI
Melusi Malinga, Isaac Lupanda, Mike Wa Nkongolo, Phil van Deventer
Large Language Model Explainable AI Low Resource Sentiment Polarity Bidirectional Encoder Representation From Transformer Multilingual Sentiment Multilingual Context
Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models
Saketh Bachu, Erfan Shayegani, Trishna Chakraborty, Rohit Lal, Arindam Dutta, Chengyu Song, Yue Dong, Nael Abu-Ghazaleh, Amit K. Roy-Chowdhury
Large Language Model Vision Language Model Multi Layer Safety Alignment Last Layer
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Haolin Chen, Yihao Feng, Zuxin Liu, Weiran Yao, Akshara Prabhakar, Shelby Heinecke, Ricky Ho, Phil Mui, Silvio Savarese, Caiming Xiong, Huan Wang
Large Language Model Language Model Reasoning Capability Capability Evolution Complex Reasoning Task Contrastive Reasoner
LSHBloom: Memory-efficient, Extreme-scale Document Deduplication
Arham Khan, Robert Underwood, Carlo Siebenschuh, Yadu Babuji, Aswathy Ajith, Kyle Hippe, Ozan Gokdemir, Alexander Brace, Kyle Chard, Ian Foster
Large Language Model Data Deduplication Memory effIcieNt
Multimodal Structure-Aware Quantum Data Processing
Hala Hawashin, Mehrnoosh Sadrzadeh
Large Language Model Natural Language Processing NLP Field Image Text Multimodal

Large Language Model

Papers

Exploring Hierarchical Molecular Graph Representation in Multimodal LLMs

Self-Calibrated Listwise Reranking with Large Language Models

Measure-to-measure interpolation using Transformers

Best Practices for Distilling Large Language Models into BERT for Web Search Ranking

Meta-Reasoning Improves Tool Use in Large Language Models

One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

DELIFT: Data Efficient Language model Instruction Fine Tuning

Bayesian Calibration of Win Rate Estimation with LLM Evaluators

Variational Low-Rank Adaptation Using IVON

Leveraging LLMs to Enable Natural Language Search on Go-to-market Platforms

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method

Benchmarking Large Language Models with Integer Sequence Generation Tasks

Measuring short-form factuality in large language models

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models

A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI

Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

LSHBloom: Memory-efficient, Extreme-scale Document Deduplication

Multimodal Structure-Aware Quantum Data Processing