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 13, 2024

Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs
Divyanshu Kumar, Umang Jain, Sahil Agarwal, Prashanth Harshangi
Large Language Model Study Feature Bias Mitigation Implicit Bias Bias Evaluation LLM Prediction
3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation
Hongxin Ding, Yue Fang, Runchuan Zhu, Xinke Jiang, Jinyang Zhang, Yongxin Xu, Xu Chu, Junfeng Zhao, Yasha Wang
Large Language Model Domain Adaptation Case Study LLM Credence
ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
Hai Huang, Randall Balestriero
Large Language Model Low Rank Adaptation

October 12, 2024

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
Yuxi Xie, Anirudh Goyal, Xiaobao Wu, Xunjian Yin, Xiao Xu, Min-Yen Kan, Liangming Pan, William Yang Wang
Large Language Model Structured Output Iterative Algorithm Coral Reef
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Jun Wang, Meng Fang, Ziyu Wan, Muning Wen, Jiachen Zhu, Anjie Liu, Ziqin Gong, Yan Song, Lei Chen, Lionel M. Ni, Linyi Yang, Ying Wen, Weinan Zhang
Large Language Model Language Model Complex Reasoning Reasoning Capability OpenAI Codex Step by Step Reasoning Open Source Framework
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
Ankita Sinha, Wendi Cui, Kamalika Das, Jiaxin Zhang
Large Language Model Optimization Purpose Prompt Optimization Single Objective Interleaving Method Deep Survival SAfER Instruct
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models
Jiaxin Zhang, Wendi Cui, Yiran Huang, Kamalika Das, Sricharan Kumar
Large Language Model Language Model Knowledge Injection Injection Drug Use Synthetic Relational Knowledge Synthesis Semantic Knowledge Emphasized Report Refinement
SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs
Mohammad Mozaffari, Maryam Mehri Dehnavi
Large Language Model Sparse Representation Quantization Aware Training Low Rank Approximation Semantic Map Pruning Quantization
Towards Scalable Semantic Representation for Recommendation
Taolin Zhang, Junwei Pan, Jinpeng Wang, Yaohua Zha, Tao Dai, Bin Chen, Ruisheng Luo, Xiaoxiang Deng, Yuan Wang, Ming Yue, Jie Jiang, Shu-Tao Xia
Large Language Model Effective Recommendation Semantic Representation LLM Embeddings Semantic ID
MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
Jiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao
Large Language Model Language Model Inductive Reasoning Deduction System
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao
Large Language Model Commonsense Reasoning Large Language Knowledge Intensive Task Commonsense Reasoning Task Online Filtering Knowledge Integration Event Linking Commonsense Reasoning Benchmark
SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs
Wenxi Chen, Ziyang Ma, Xiquan Li, Xuenan Xu, Yuzhe Liang, Zhisheng Zheng, Kai Yu, Xie Chen
Large Language Model Fine Grained Speech Recognition Audio Captioning
Debiasing Vison-Language Models with Text-Only Training
Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming Zhang, Jitao Sang
Large Language Model Vision Language Model Multi Target Visual Bias Text Only Training
Inference and Verbalization Functions During In-Context Learning
Junyi Tao, Xiaoyin Chen, Nelson F. Liu
Large Language Model Context Learning Scientific Inference Inference Framework
ELICIT: LLM Augmentation via External In-Context Capability
Futing Wang, Jianhao Yan, Yue Zhang, Tao Lin
Large Language Model Context Learning Task Vector Eliciting Knowledge Elicitation Method LLM Based Augmentation
LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models
Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Rongqiao An, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun
Large Language Model Language Model Long Text Long Context Large Language Model Content Analysis Long Sequence Processing Hadoop MapReduce
Keys to Robust Edits: from Theoretical Insights to Practical Advances
Jianhao Yan, Futing Wang, Yun Luo, Yafu Li, Yue Zhang
Large Language Model Theoretical Analysis Knowledge Editing Practical Application Key Value Secret Key

October 11, 2024

Nudging: Inference-time Alignment via Model Collaboration
Yu Fei, Yasaman Razeghi, Sameer Singh
Large Language Model Token Level Training Free Temporal Alignment LLM Alignment Model Collaboration Aligned Model
One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks
Anastasiia Birillo, Elizaveta Artser, Anna Potriasaeva, Ilya Vlasov, Katsiaryna Dzialets, Yaroslav Golubev, Igor Gerasimov, Hieke Keuning, Timofey Bryksin
Large Language Model Cross Over Step Programming Task Static Analysis Natural Language Hint Next Step Hint Generation
LLMD: A Large Language Model for Interpreting Longitudinal Medical Records
Robert Porter, Adam Diehl, Benjamin Pastel, J. Henry Hinnefeld, Lawson Nerenberg, Pye Maung, Sebastien Kerbrat, Gillian Hanson, Troy Astorino, Stephen J. Tarsa
Large Language Model Raw Data Domain Knowledge Patient Data Medical Benchmark

Large Language Model

Papers

Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs

3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution

Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models

SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs

Towards Scalable Semantic Representation for Recommendation

MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning

SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs

Debiasing Vison-Language Models with Text-Only Training

Inference and Verbalization Functions During In-Context Learning

ELICIT: LLM Augmentation via External In-Context Capability

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models

Keys to Robust Edits: from Theoretical Insights to Practical Advances

Nudging: Inference-time Alignment via Model Collaboration

One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks

LLMD: A Large Language Model for Interpreting Longitudinal Medical Records