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 2, 2024

Spoken Grammar Assessment Using LLM
Sunil Kumar Kopparapu, Chitralekha Bhat, Ashish Panda
Large Language Model Proficiency Vector Spoken Language Assessment
Integrative Decoding: Improve Factuality via Implicit Self-consistency
Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao, Song Wang, Yuji Zhang, Wenjun Hou, Kaishuai Xu, Wenge Liu, Wenjie Li, Jian Jiao, Qi Chen, Peng Cheng, Wayne Xiong
Large Language Model Language Model Factual Claim Self Consistency Open Ended Generation
MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE Framework
Zonghai Yao, Zihao Zhang, Chaolong Tang, Xingyu Bian, Youxia Zhao, Zhichao Yang, Junda Wang, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Hong Yu
Large Language Model Multiple Choice Artificial Intelligence Framework MedQA Dataset Medical Multimodal
In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks
Dingzirui Wang, Xuanliang Zhang, Qiguang Chen, Longxu Dou, Xiao Xu, Rongyu Cao, Yingwei Ma, Qingfu Zhu, Wanxiang Che, Binhua Li, Fei Huang, Yongbin Li
Large Language Model Context Learning Task Similarity Task Demonstration
Getting in the Door: Streamlining Intake in Civil Legal Services with Large Language Models
Quinten Steenhuis, Hannes Westermann
Large Language Model Legal Text Legal Article Eligibility Criterion Streamlined Approach
Extending Context Window of Large Language Models from a Distributional Perspective
Yingsheng Wu. Yuxuan Gu, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin
Large Language Model Long Sequence LLM Benchmark Context Window Distributional Perspective
From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge
Xiefeng Wu
Large Language Model Reinforcement Learning Reward Shaping Unbiased Learning Q Value
House of Cards: Massive Weights in LLMs
Jaehoon Oh, Seungjun Shin, Dokwan Oh
Large Language Model Balancing Weight Targeted Activation Penalty Weight Freezing
Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao, Shafiq Joty, Lidong Bing
Large Language Model Reinforcement Learning Complex Reasoning Task Planning Retrieval Augmentation Complex Task Critic Model
Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias
Federico Torrielli
Large Language Model Language Model Artificial Intelligence ChatGPT Generated Conversation Grayscale Image Intersectional Bias Silicon Atom
Getting Free Bits Back from Rotational Symmetries in LLMs
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Large Language Model Multiplier Free Quantization Neural Network Weight P Bit
Emotion-Aware Response Generation Using Affect-Enriched Embeddings with LLMs
Abdur Rasool, Muhammad Irfan Shahzad, Hafsa Aslam, Vincent Chan
Large Language Model Jina Embeddings Emotion Embeddings Emotion Lexicon
Speculative Coreset Selection for Task-Specific Fine-tuning
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Tianlin Li, Weipeng Jiang, Yang Liu
Large Language Model Task Specific COreset Selection
Mitigating Copy Bias in In-Context Learning through Neuron Pruning
Ameen Ali, Lior Wolf, Ivan Titov
Large Language Model Context Learning Mitigating Bias Shot Scenario Synthetic Task Task Vector Neuron Pruning
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration
Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng
Large Language Model Image Denoiser Training Data Attribution Attribution Mask
Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models
Can Demircan, Tankred Saanum, Akshay K. Jagadish, Marcel Binz, Eric Schulz
Large Language Model Reinforcement Learning Context Learning Sparse Autoencoders
AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
Xiaotian Lu, Jiyi Li, Koh Takeuchi, Hisashi Kashima
Large Language Model Natural Language Processing Open Ended LLM Reasoning Multi Criterion Open Ended Response
Automatic deductive coding in discourse analysis: an application of large language models in learning analytics
Lishan Zhang, Han Wu, Xiaoshan Huang, Tengfei Duan, Hanxiang Du
Large Language Model Language Model Discourse Structure Data Analytics Automatic Page Discourse Analysis
ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving
Yifan Qiao, Shu Anzai, Shan Yu, Haoran Ma, Yang Wang, Miryung Kim, Harry Xu
Large Language Model Language Model LLM Inference Low Latency Inference Task GPU Cluster Environmental Conservation
StringLLM: Understanding the String Processing Capability of Large Language Models
Xilong Wang, Hao Fu, Neil Zhenqiang Gong
Large Language Model Natural Language Processing String Problem

Large Language Model

Papers

Spoken Grammar Assessment Using LLM

Integrative Decoding: Improve Factuality via Implicit Self-consistency

MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE Framework

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks

Getting in the Door: Streamlining Intake in Civil Legal Services with Large Language Models

Extending Context Window of Large Language Models from a Distributional Perspective

From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge

House of Cards: Massive Weights in LLMs

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias

Getting Free Bits Back from Rotational Symmetries in LLMs

Emotion-Aware Response Generation Using Affect-Enriched Embeddings with LLMs

Speculative Coreset Selection for Task-Specific Fine-tuning

Mitigating Copy Bias in In-Context Learning through Neuron Pruning

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses

Automatic deductive coding in discourse analysis: an application of large language models in learning analytics

ConServe: Harvesting GPUs for Low-Latency and High-Throughput Large Language Model Serving

StringLLM: Understanding the String Processing Capability of Large Language Models