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

October 11, 2024

SocialGaze: Improving the Integration of Human Social Norms in Large Language Models
Anvesh Rao Vijjini, Rakesh R. Menon, Jiayi Fu, Shashank Srivastava, Snigdha Chaturvedi
Large Language Model Language Model Consensus Group Decision Human Judgment Linguistic Acceptability Human Norm
DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
Yanfeng Jiang, Zelan Yang, Bohua Chen, Shen Li, Yong Li, Tao Li
Large Language Model Structured Dropout Fine Tuned LLM Group Wise Delta Compression
QEFT: Quantization for Efficient Fine-Tuning of LLMs
Changhun Lee, Jun-gyu Jin, Younghyun Cho, Eunhyeok Park
Large Language Model Fine Tuning Medical LLM Parameter Efficient Fine Tuning Quantization Operator Inference Speed
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Priyanshu Kumar, Elaine Lau, Saranya Vijayakumar, Tu Trinh, Scale Red Team, Elaine Chang, Vaughn Robinson, Sean Hendryx, Shuyan Zhou, Matt Fredrikson, Summer Yue, Zifan Wang
Large Language Model Red Teaming Web Agent Safe Agent Malicious Domain
Scaling Laws for Predicting Downstream Performance in LLMs
Yangyi Chen, Binxuan Huang, Yifan Gao, Zhengyang Wang, Jingfeng Yang, Heng Ji
Large Language Model Language Model Domain Specific Scaling Law Performance Estimation Downstream Model Downstream Performance
$\forall$uto$\exists$$\lor\!\land$L: Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks
Rushang Karia, Daniel Bramblett, Daksh Dobhal, Siddharth Srivastava
Large Language Model Medical LLM Reasoning Task Fact Checking Novel Benchmark Efficient Annotation

October 10, 2024

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
Sitao Cheng, Liangming Pan, Xunjian Yin, Xinyi Wang, William Yang Wang
Large Language Model Contextual Information Knowledge Intensive Task Parametric Model Parametric Knowledge Contextual Knowledge
Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks
Mahmood Hegazy
Large Language Model Complex Reasoning Diversity Awareness Multi Agent Debate Thought Prompting
Language model developers should report train-test overlap
Andy K Zhang, Kevin Klyman, Yifan Mai, Yoav Levine, Yian Zhang, Rishi Bommasani, Percy Liang
Large Language Model Language Model Train Test
VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models
Lisa Dunlap, Krishna Mandal, Trevor Darrell, Jacob Steinhardt, Joseph E Gonzalez
Large Language Model Language Model Qualitative Difference Model Behavior
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, Ji-Rong Wen
Large Language Model Environment Exploration Expert Knowledge Tool Learning Autonomous Behavior Tool Documentation
Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System
Weize Chen, Jiarui Yuan, Chen Qian, Cheng Yang, Zhiyuan Liu, Maosong Sun
Large Language Model High Efficiency Multi Agent System Agent System Multi Agent Task
A Closer Look at Machine Unlearning for Large Language Models
Xiaojian Yuan, Tianyu Pang, Chao Du, Kejiang Chen, Weiming Zhang, Min Lin
Large Language Model Machine Unlearning Unlearning Framework Unlearning Method Closer Look
What Makes Large Language Models Reason in (Multi-Turn) Code Generation?
Kunhao Zheng, Juliette Decugis, Jonas Gehring, Taco Cohen, Benjamin Negrevergne, Gabriel Synnaeve
Large Language Model Code Generation Reasoning Process Competitive Programming
Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining
Tianyi Bai, Ling Yang, Zhen Hao Wong, Jiahui Peng, Xinlin Zhuang, Chi Zhang, Lijun Wu, Qiu Jiantao, Wentao Zhang, Binhang Yuan, Conghui He
Large Language Model Language Model Pre Trained Data Selection Multi Agent Framework
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
Shenao Zhang, Zhihan Liu, Boyi Liu, Yufeng Zhang, Yingxiang Yang, Yongfei Liu, Liyu Chen, Tao Sun, Zhaoran Wang
Large Language Model Preference Alignment Implicit Reward Preference Dataset
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation
Tomas Bueno Momcilovic, Beat Buesser, Giulio Zizzo, Mark Purcell, Tomas Bueno Momcilovic
Large Language Model Adversarial Attack Adversarial Training Adversarial Robustness Argumentative Explanation
Efficient Reinforcement Learning with Large Language Model Priors
Xue Yan, Yan Song, Xidong Feng, Mengyue Yang, Haifeng Zhang, Haitham Bou Ammar, Jun Wang
Large Language Model Reinforcement Learning Prior Knowledge Efficient Reinforcement Learning Action Prior
Scalable Representation Learning for Multimodal Tabular Transactions
Natraj Raman, Sumitra Ganesh, Manuela Veloso
Large Language Model Representation Learning Large Scale Dataset Cross Task Knowledge Tabular Representation Learning High Cardinality
Mitigating Gender Bias in Code Large Language Models via Model Editing
Zhanyue Qin, Haochuan Wang, Zecheng Wang, Deyuan Liu, Cunhang Fan, Zhao Lv, Zhiying Tu, Dianhui Chu, Dianbo Sui
Large Language Model Code Generation Gender Bias Model Editing Code Datasets

Large Language Model

Papers

SocialGaze: Improving the Integration of Human Social Norms in Large Language Models

DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization

QEFT: Quantization for Efficient Fine-Tuning of LLMs

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Scaling Laws for Predicting Downstream Performance in LLMs

$\forall$uto$\exists$$\lor\!\land$L: Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models

Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks

Language model developers should report train-test overlap

VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System

A Closer Look at Machine Unlearning for Large Language Models

What Makes Large Language Models Reason in (Multi-Turn) Code Generation?

Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining

Reward-Augmented Data Enhances Direct Preference Alignment of LLMs

Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation

Efficient Reinforcement Learning with Large Language Model Priors

Scalable Representation Learning for Multimodal Tabular Transactions

Mitigating Gender Bias in Code Large Language Models via Model Editing