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 31, 2024

The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams
Yunqi Zhu, Wen Tang, Ying Sun, Xuebing Yang
Large Language Model Yes No Question Top Two Answer Medical Report Generation Exam Document State Medical Licensing Examination Medical Student Large Scale Chinese
DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi Yang, Yulin Yuan, Lidia S. Chao
Large Language Model Real World Benchmark Platform Multi Scenario Text Detection LLM Detector
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Ming Li, Yanhong Li, Tianyi Zhou
Large Language Model Natural Gradient Efficient Planning
Evolving Alignment via Asymmetric Self-Play
Ziyu Ye, Rishabh Agarwal, Tianqi Liu, Rishabh Joshi, Sarmishta Velury, Quoc V. Le, Qijun Tan, Yuan Liu
Large Language Model Self Play RLHF V Automatic Alignment Agnostic Alignment
Dynamic Uncertainty Ranking: Enhancing In-Context Learning for Long-Tail Knowledge in LLMs
Shuyang Yu, Runxue Bao, Parminder Bhatia, Taha Kass-Hout, Jiayu Zhou, Cao Xiao
Large Language Model Context Learning Question Answering Knowledge Based Long Tail
ALISE: Accelerating Large Language Model Serving with Speculative Scheduling
Youpeng Zhao, Jun Wang
Large Language Model LLM Inference Task Scheduling Memory Management Speculative Exploration Latency Constraint
LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
Hieu Tran, Junda Wang, Yujan Ting, Weijing Huang, Terrence Chen
Large Language Model LeArning Abstract Fact Checking Natural Language Processing Task Factual Claim Front End

October 30, 2024

Tiny Transformers Excel at Sentence Compression
Peter Belcak, Roger Wattenhofer
Large Language Model Sub Byte Tiny Transformer Sentence Compression
Smaller Large Language Models Can Do Moral Self-Correction
Guangliang Liu, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson
Large Language Model Language Model Self Correction
Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?
Yue Huang, Zhengqing Yuan, Yujun Zhou, Kehan Guo, Xiangqi Wang, Haomin Zhuang, Weixiang Sun, Lichao Sun, Jindong Wang, Yanfang Ye, Xiangliang Zhang
Large Language Model Simulation Study Social Science Social Simulation LLM Simulation
Dynamic Information Sub-Selection for Decision Support
Hung-Tien Huang, Maxwell Lennon, Shreyas Bhat Brahmavar, Sean Sylvia, Junier B. Oliva
Large Language Model Black Box AI Assistance Decision Support
ACC-Debate: An Actor-Critic Approach to Multi-Agent Debate
Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
Large Language Model Actor Critic Natural Language Task Multi Agent Debate
Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
Chenyang An, Shima Imani, Feng Yao, Chengyu Dong, Ali Abbasi, Harsh Shrivastava, Samuel Buss, Jingbo Shang, Gayathri Mahalingam, Pramod Sharma, Maurice Diesendruck
Large Language Model Training Data Propositional Logic Proof Generation Computation Tree Logic
Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists
Michał Pietruszka, Łukasz Borchmann, Aleksander Jędrosz, Paweł Morawiecki
Large Language Model Full Model Medical LLM Raw Data Domain Knowledge Science Journalism Deep Understanding Feature Engineering Knowledge Intensive Task Base Model
Evaluating Cultural and Social Awareness of LLM Web Agents
Haoyi Qiu, Alexander R. Fabbri, Divyansh Agarwal, Kung-Hsiang Huang, Sarah Tan, Nanyun Peng, Chien-Sheng Wu
Large Language Model NLP Task Social Awareness Web Agent
A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment
Matteo G. Mecattaf, Ben Slater, Marko Tešić, Jonathan Prunty, Konstantinos Voudouris, Lucy G. Cheke
Large Language Model Complex Reasoning Environment Feature Cognitive Science Physical Reasoning Limited Communication Physical Commonsense
Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
Sheryl Hsu, Omar Khattab, Chelsea Finn, Archit Sharma
Large Language Model Search Query Positive Reinforcement Retrieval Performance Retrieval Enhanced Preference Based Optimization
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Yiruo Cheng, Kelong Mao, Ziliang Zhao, Guanting Dong, Hongjin Qian, Yongkang Wu, Tetsuya Sakai, Ji-Rong Wen, Zhicheng Dou
Large Language Model Retrieval Augmented Generation Faithful Generation Benchmark Platform Multi Turn Conversation Coral Reef
BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference
Junqi Zhao, Zhijin Fang, Shu Li, Shaohui Yang, Shichao He
Large Language Model Natural Language Processing LLM Inference Key Value Cache Long Document Summarization Private Aggregation Inference Speedup
Multi-Programming Language Sandbox for LLMs
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Shaoqing Zhang, Muling Wu, Changze Lv, Limao Xiong, Wenyu Zhan, Lin Zhang, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Rui Zheng, Tao Ji, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
Large Language Model Programming Task Code LLM Tool Augmented LLM End to End Compiler

Large Language Model

Papers

The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Evolving Alignment via Asymmetric Self-Play

Dynamic Uncertainty Ranking: Enhancing In-Context Learning for Long-Tail Knowledge in LLMs

ALISE: Accelerating Large Language Model Serving with Speculative Scheduling

LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models

Tiny Transformers Excel at Sentence Compression

Smaller Large Language Models Can Do Moral Self-Correction

Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?

Dynamic Information Sub-Selection for Decision Support

ACC-Debate: An Actor-Critic Approach to Multi-Agent Debate

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation

Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists

Evaluating Cultural and Social Awareness of LLM Web Agents

A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment

Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation

BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference

Multi-Programming Language Sandbox for LLMs