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 4, 2024

Detecting Machine-Generated Long-Form Content with Latent-Space Variables
Yufei Tian, Zeyu Pan, Nanyun Peng
Large Language Model Data Detection Latent Space Generated Text Long Text Paragraph Speech
Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style
Ziyang Chen, Stylios Moscholios
Large Language Model Complex Prompt Conversational AI
Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs
Tomas Bueno Momcilovic, Dian Balta, Beat Buesser, Giulio Zizzo, Mark Purcell
Large Language Model Adversarial Attack Adversarial Robustness Security Vulnerability LLM Safety Regulatory Compliance Assurance Case
Enhance Reasoning by Learning from Mistakes: Peer-Review Knowledge Distillation from Multiple Large Language Models
Zhuochun Li, Yuelyu Ji, Rui Meng, Daqing He
Large Language Model Knowledge Distillation Reasoning Task Reasoning Capability Reasoning Ability Peer Review Human Answer Mistake Impressive Reasoning Capability
RAFT: Realistic Attacks to Fool Text Detectors
James Wang, Ran Li, Junfeng Yang, Chengzhi Mao
Large Language Model Language Model Black Box Attack LLM Embeddings Real World Attack LLM Detector
Aligning LLMs with Individual Preferences via Interaction
Shujin Wu, May Fung, Cheng Qian, Jeonghwan Kim, Dilek Hakkani-Tur, Heng Ji
Large Language Model Interaction Generation Multi Turn Conversation Large Language Model Alignment Preference Datasets Personalized Alignment Interest Preference
Large Language Models can be Strong Self-Detoxifiers
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Youssef Mroueh, Soham Dan, Georgios Kollias, Subhajit Chaudhury, Tejaswini Pedapati, Luca Daniel
Large Language Model Language Model Autoregressive Sequence Fine Grained Detoxification Toxicity Mitigation
Large Language Model Performance Benchmarking on Mobile Platforms: A Thorough Evaluation
Jie Xiao, Qianyi Huang, Xu Chen, Chen Tian
Large Language Model Language Model Mobile Application Lightweight Large Language Model LLM App
Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)
Abrar Rahman, Garry Bowlin, Binit Mohanty, Sean McGunigal
Large Language Model Tokenization Matter Various Number Specific Tokenization Scheme
Llettuce: An Open Source Natural Language Processing Tool for the Translation of Medical Terms into Uniform Clinical Encoding
James Mitchell-White, Reza Omdivar, Esmond Urwin, Karthikeyan Sivakumar, Ruizhe Li, Andy Rae, Xiaoyan Wang, Theresia Mina, John Chambers, Grazziela Figueredo, Philip R Quinlan
Large Language Model Natural Language Processing View Translation Medical Text Domain Based Nuance Health Metric
LLMProxy: Reducing Cost to Access Large Language Models
Noah Martin, Abdullah Bin Faisal, Hiba Eltigani, Rukhshan Haroon, Swaminathan Lamelas, Fahad Dogar
Large Language Model Hidden CoST Information Access System Optimization
Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores
Robert E. Blackwell, Jon Barry, Anthony G. Cohn
Large Language Model New Benchmark Uncertainty Quantification Benchmark Study Deterministic Algorithm LLM Benchmark
Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation
Tobias Leemann, Periklis Petridis, Giuseppe Vietri, Dionysis Manousakas, Aaron Roth, Sergul Aydore
Large Language Model Domain Adaptation Retrieval Augmented Generation Natural Language Inference Bottom Up Grounding
How Toxicity Classifiers and Large Language Models Respond to Ableism
Mahika Phutane, Ananya Seelam, Aditya Vashistha
Large Language Model Social Bias Toxicity Detection
On Uncertainty In Natural Language Processing
Dennis Ulmer
Large Language Model Natural Language Processing Uncertainty Quantification Language Generation High Uncertainty Anticipation Black Box Large Language Model
ToolGen: Unified Tool Retrieval and Calling via Generation
Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, Haonan Li
Large Language Model Faithful Generation Language Generation Tool Learning Tool Retrieval
One2set + Large Language Model: Best Partners for Keyphrase Generation
Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su
Large Language Model Keyphrase Generation Author Assigned Keyphrases Channel Partner Level
Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models
Pavel Stepachev, Pinzhen Chen, Barry Haddow
Large Language Model Context Information
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Haibo Wang, Zhiyang Xu, Yu Cheng, Shizhe Diao, Yufan Zhou, Yixin Cao, Qifan Wang, Weifeng Ge, Lifu Huang
Large Language Model Temporal Grounding Temporal Sentence Grounding Fine Grained Video
What do Large Language Models Need for Machine Translation Evaluation?
Shenbin Qian, Archchana Sindhujan, Minnie Kabra, Diptesh Kanojia, Constantin Orăsan, Tharindu Ranasinghe, Frédéric Blain
Large Language Model Machine Translation Natural Language Processing Task Multilingual Pre Trained Language Model LLM Based Evaluation Machine Translation Evaluation

Large Language Model

Papers

Detecting Machine-Generated Long-Form Content with Latent-Space Variables

Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style

Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs

Enhance Reasoning by Learning from Mistakes: Peer-Review Knowledge Distillation from Multiple Large Language Models

RAFT: Realistic Attacks to Fool Text Detectors

Aligning LLMs with Individual Preferences via Interaction

Large Language Models can be Strong Self-Detoxifiers

Large Language Model Performance Benchmarking on Mobile Platforms: A Thorough Evaluation

Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)

Llettuce: An Open Source Natural Language Processing Tool for the Translation of Medical Terms into Uniform Clinical Encoding

LLMProxy: Reducing Cost to Access Large Language Models

Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores

Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation

How Toxicity Classifiers and Large Language Models Respond to Ableism

On Uncertainty In Natural Language Processing

ToolGen: Unified Tool Retrieval and Calling via Generation

One2set + Large Language Model: Best Partners for Keyphrase Generation

Context and System Fusion in Post-ASR Emotion Recognition with Large Language Models

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

What do Large Language Models Need for Machine Translation Evaluation?