Llama 2: Open Foundation and Fine-Tuned Chat Models

Abstract

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.

Cited by in corpus (181)

• A Survey on Large Language Model based Autonomous Agents
• A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
• Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization
• A Survey on Multimodal Large Language Models
• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• Large Language Models (LLMs) as Agents for Augmented Democracy
• Large language models in medicine: the potentials and pitfalls
• Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering
• Unleashing the potential of prompt engineering for large language models
• Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
• Large AI Models in Health Informatics: Applications, Challenges, and the Future
• Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review
• ChatEDA: A Large Language Model Powered Autonomous Agent for EDA
• Large language models surpass human experts in predicting neuroscience results
• Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education
• Materials science in the era of large language models: a perspective
• A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization
• Diffusion Model-Based Image Editing: A Survey
• ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case Application
• A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine
• Evaluation of large language models for discovery of gene set function
• General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance
• CLIP in Medical Imaging: A Survey
• Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference
• UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
• The Dawn of Natural Language to SQL: Are We Fully Ready?
• Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
• Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis
• ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs
• Image and Data Mining in Reticular Chemistry Using GPT-4V
• LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
• Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models
• Exploring the psychology of LLMs' Moral and Legal Reasoning
• Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
• AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events
• Language Models as Zero-Shot Trajectory Generators
• Text Clustering with Large Language Model Embeddings
• Leveraging LLMs for the Quality Assurance of Software Requirements
• HPC-GPT: Integrating Large Language Model for High-Performance Computing
• A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
• MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• El Agente: An Autonomous Agent for Quantum Chemistry
• Embedding Large Language Models into Extended Reality: Opportunities and Challenges for Inclusion, Engagement, and Privacy
• The Moral Machine Experiment on Large Language Models
• Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain
• Mask-guided BERT for Few Shot Text Classification
• Enhanced Automated Code Vulnerability Repair using Large Language Models
• Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models
• Enhancing textual textbook question answering with large language models and retrieval augmented generation
• Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
• Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: a Survey
• Developing ChemDFM as a large language foundation model for chemistry
• Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
• Large language models as oracles for instantiating ontologies with domain-specific knowledge
• Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking
• Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
• QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
• Clinical Insights: A Comprehensive Review of Language Models in Medicine
• Dual Use Concerns of Generative AI and Large Language Models
• A Survey on Contextualised Semantic Shift Detection
• Playing with words: Comparing the vocabulary and lexical diversity of ChatGPT and humans
• Large language models for automated scholarly paper review: A survey
• Improving the Validity of Automatically Generated Feedback via Reinforcement Learning
• A Framework for Neurosymbolic Robot Action Planning using Large Language Models
• Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)
• Domain Terminology Integration into Machine Translation: Leveraging Large Language Models
• An evolutionary model of personality traits related to cooperative behavior using a large language model
• A Reliable Knowledge Processing Framework for Combustion Science using Foundation Models
• Transfer Learning with Foundational Models for Time Series Forecasting using Low-Rank Adaptations
• Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation
• CoVR-2: Automatic Data Construction for Composed Video Retrieval
• Few-Shot Panoptic Segmentation With Foundation Models
• ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation
• RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering
• Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
• Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?
• Exploring Large Language Models to generate Easy to Read content
• Computational Argumentation-based Chatbots: a Survey
• LLM-based feature generation from text for interpretable machine learning
• ShennongAlpha: an AI-driven sharing and collaboration platform for intelligent curation, acquisition, and translation of natural medicinal material knowledge
• Pre-Trained Language Models for Keyphrase Prediction: A Review
• Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field
• Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning
• Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality
• Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
• Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges
• Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive
• Discrete Prompt Compression with Reinforcement Learning
• Deep learning for nano-photonic materials -- The solution to everything!?
• Speed and Conversational Large Language Models: Not All Is About Tokens per Second
• Tucano: Advancing Neural Text Generation for Portuguese
• Relax: Composable Abstractions for End-to-End Dynamic Machine Learning
• Comparison of Large Language Models for Generating Contextually Relevant Questions
• Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
• MedDoc-Bot: A Chat Tool for Comparative Analysis of Large Language Models in the Context of the Pediatric Hypertension Guideline
• Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models
• SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers
• Fusing Domain-Specific Content from Large Language Models into Knowledge Graphs for Enhanced Zero Shot Object State Classification
• Open Scene Graphs for Open-World Object-Goal Navigation
• A Survey of Large Language Models for Arabic Language and its Dialects
• CANAL -- Cyber Activity News Alerting Language Model: Empirical Approach vs. Expensive LLM
• Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis
• Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading
• LLMs and Stack Overflow Discussions: Reliability, Impact, and Challenges
• Large Language Models for Combinatorial Optimization: A Systematic Review
• Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
• Breaking the Memory Wall: A Study of I/O Patterns and GPU Memory Utilization for Hybrid CPU-GPU Offloaded Optimizers
• Normative Conflicts and Shallow AI Alignment
• On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software
• Advancing biomolecular understanding and design following human instructions
• Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classification
• RAGE Against the Machine: Retrieval-Augmented LLM Explanations
• Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
• Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models
• A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
• Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data
• DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning
• Relational Programming with Foundation Models
• LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
• Improving the Capabilities of Large Language Model Based Marketing Analytics Copilots With Semantic Search And Fine-Tuning
• TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
• Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation
• MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity
• Mosaic: Composite Projection Pruning for Resource-efficient LLMs
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
• CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
• AdditiveLLM: Large Language Models Predict Defects in Additive Manufacturing
• Network Formation and Dynamics Among Multi-LLMs
• Had enough of experts? Quantitative knowledge retrieval from large language models
• Evaluating Language Model Agency through Negotiations
• CCA: Collaborative Competitive Agents for Image Editing
• Visual Hindsight Self-Imitation Learning for Interactive Navigation
• ESG Accountability Made Easy: DocQA at Your Service
• Optimal strategies to perform multilingual analysis of social content for a novel dataset in the tourism domain
• Flows: Building Blocks of Reasoning and Collaborating AI
• Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study
• A semantic embedding space based on large language models for modelling human beliefs
• Visual Analysis of LLM-based Entity Resolution from Scientific Papers
• AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database
• Camera Control at the Edge with Language Models for Scene Understanding
• Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
• OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses
• Speaker attribution in German parliamentary debates with QLoRA-adapted large language models
• Automated Spinal MRI Labelling from Reports Using a Large Language Model
• Divergences between Language Models and Human Brains
• Evaluation of Geographical Distortions in Language Models
• Evaluating the Reliability of Self-Explanations in Large Language Models
• Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science
• MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains
• Guarding Your Conversations: Privacy Gatekeepers for Secure Interactions with Cloud-Based AI Models
• CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
• Automated Annotation of Scientific Texts for ML-based Keyphrase Extraction and Validation
• Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models
• Are the Majority of Public Computational Notebooks Pathologically Non-Executable?
• QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models
• A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
• SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation
• Multi-Task Learning for Front-End Text Processing in TTS
• Annotating Scientific Uncertainty: A comprehensive model using linguistic patterns and comparison with existing approaches
• DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction
• Wiki-TabNER: Integrating Named Entity Recognition into Wikipedia Tables
• A Comprehensive Evaluation of Semantic Relation Knowledge of Pretrained Language Models and Humans
• Emergent inabilities? Inverse scaling over the course of pretraining
• Collaborating Foundation Models for Domain Generalized Semantic Segmentation
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention
• ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling
• Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
• Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
• GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models
• Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines
• A Unified Approach to Emotion Detection and Task-Oriented Dialogue Modeling
• English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance
• It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models
• Do Large Language Models know who did what to whom?
• Vectorizing string entries for data processing on tables: when are larger language models better?
• Searching Personal Collections
• AI-generated text boundary detection with RoFT
• A Roadmap for Tamed Interactions with Large Language Models
• Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation