Articoli scientifici

Di seguito sono riportati gli articoli scientifici più recenti (ordinati in base alla data di pubblicazione) sul prompt engineering. Aggiorniamo questa guida quotidianamente, in base all'arrivo di nuovi documenti. Ogni settimana inseriamo i riassunti di questi documenti nelle guide precedenti.

Panoramica

A Survey of Large Language Models (opens in a new tab) (Aprile 2023)
Nature Language Reasoning, A Survey (opens in a new tab) (Marzo 2023)
Augmented Language Models: a Survey (opens in a new tab) (Febbraio 2023)
A Survey for In-context Learning (opens in a new tab) (Dicembre 2022)
Towards Reasoning in Large Language Models: A Survey (opens in a new tab) (Dicembre 2022)
Reasoning with Language Model Prompting: A Survey (opens in a new tab) (Dicembre 2022)
Emergent Abilities of Large Language Models (opens in a new tab) (Giugno 2022)
A Taxonomy of Prompt Modifiers for Text-To-Image Generation (opens in a new tab) (Aprile 2022)
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (opens in a new tab) (Jul 2021)

Approcci

CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society (opens in a new tab) (Marzo 2023)
Self-Refine: Iterative Refinement with Self-Feedback (opens in a new tab) (Marzo 2023)
kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference (opens in a new tab) (Marzo 2023)
Visual-Language Prompt Tuning with Knowledge-guided Context Optimization (opens in a new tab) (Marzo 2023)
Fairness-guided Few-shot Prompting for Large Language Models (opens in a new tab) (Marzo 2023)
Context-faithful Prompting for Large Language Models (opens in a new tab) (Marzo 2023)
Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning (opens in a new tab) (Marzo 2023)
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (opens in a new tab) (Marzo 2023)
Model-tuning Via Prompts Makes NLP Models Adversarially Robust (opens in a new tab) (Marzo 2023)
Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer (opens in a new tab) (Marzo 2023)
CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification (opens in a new tab) (Marzo 2023)
Larger language models do in-context learning differently (opens in a new tab) (Marzo 2023)
OpenICL: An Open-Source Framework for In-context Learning (opens in a new tab) (Marzo 2023)
Dynamic Prompting: A Unified Framework for Prompt Tuning (opens in a new tab) (Marzo 2023)
Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning (opens in a new tab) (Marzo 2023)
Effectiveness of Data Augmentation for Prefix Tuning with Limited Data (opens in a new tab) (Marzo 2023)
Mixture of Soft Prompts for Controllable Data Generation (opens in a new tab) (Marzo 2023)
Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners (opens in a new tab) (Marzo 2023)
How Robust is GPT-3.5 to PreDicembreessors? A Comprehensive Study on Language Understanding Tasks (opens in a new tab) (Marzo 2023)
Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT (opens in a new tab) (Febbraio 2023)
EvoPrompting: Language Models for Code-Level Neural Architecture Search (opens in a new tab) (Febbraio 2023)
In-Context Instruction Learning (opens in a new tab) (Febbraio 2023)
Chain of Hindsight Aligns Language Models with Feedback (opens in a new tab) (Febbraio 2023)
Language Is Not All You Need: Aligning Perception with Language Models (opens in a new tab) (Febbraio 2023)
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data (opens in a new tab) (Febbraio 2023)
Active Prompting with Chain-of-Thought for Large Language Models (opens in a new tab) (Febbraio 2023)
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models (opens in a new tab) (Febbraio 2023)
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT (opens in a new tab) (Febbraio 2023)
Guiding Large Language Models via Directional Stimulus Prompting (opens in a new tab) (Febbraio 2023)
How Does In-Context Learning Help Prompt Tuning? (opens in a new tab) (Febbraio 2023)
Scalable Prompt Generation for Semi-supervised Learning with Language Models (opens in a new tab) (Febbraio 2023)
Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints (opens in a new tab) (Febbraio 2023)
À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting (opens in a new tab) (Febbraio 2023)
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks (opens in a new tab) (Febbraio 2023)
The Capacity for Moral Self-Correction in Large Language Models (opens in a new tab) (Febbraio 2023)
SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains (opens in a new tab) (Febbraio 2023)
Evaluating the Robustness of Discrete Prompts (opens in a new tab) (Febbraio 2023)
Compositional Exemplars for In-context Learning (opens in a new tab) (Febbraio 2023)
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery (opens in a new tab) (Febbraio 2023)
Multimodal Chain-of-Thought Reasoning in Language Models (opens in a new tab) (Febbraio 2023)
Large Language Models Can Be Easily Distracted by Irrelevant Context (opens in a new tab) (Febbraio 2023)
Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models (opens in a new tab) (Febbraio 2023)
Progressive Prompts: Continual Learning for Language Models (opens in a new tab) (Gennaio 2023)
Batch Prompting: Efficient Inference with LLM APIs (opens in a new tab) (Gennaio 2023)
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP (opens in a new tab) (Dicembre 2022)
On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning (opens in a new tab) (Dicembre 2022)
Constitutional AI: Harmlessness from AI Feedback (opens in a new tab) (Dicembre 2022)
Successive Prompting for Dicembreomposing Complex Questions (opens in a new tab) (Dicembre 2022)
Large Language Models are reasoners with Self-Verification (opens in a new tab) (Dicembre 2022)
Discovering Language Model Behaviors with Model-Written Evaluations (opens in a new tab) (Dicembre 2022)
Structured Prompting: Scaling In-Context Learning to 1,000 Examples (opens in a new tab) (Dicembre 2022)
PAL: Program-aided Language Models (opens in a new tab) (Novembre 2022)
Large Language Models Are Human-Level Prompt Engineers (opens in a new tab) (Novembre 2022)
Ignore Previous Prompt: Attack Techniques For Language Models (opens in a new tab) (Novembre 2022)
Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods (opens in a new tab) (Novembre 2022)
Teaching Algorithmic Reasoning via In-context Learning (opens in a new tab) (Novembre 2022)
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference (opens in a new tab) (Novembre 2022)
Ask Me Anything: A simple strategy for prompting language models (opens in a new tab) (Ottobre 2022)
Recitation-Augmented Language Models (opens in a new tab) (Ottobre 2022)
ReAct: Synergizing Reasoning and Acting in Language Models (opens in a new tab) (Ottobre 2022)
Prompting GPT-3 To Be Reliable (opens in a new tab) (Ottobre 2022)
Dicembreomposed Prompting: A Modular Approach for Solving Complex Tasks (opens in a new tab) (Ottobre 2022)
Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought (opens in a new tab) (Ottobre 2022)
Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples (opens in a new tab) (Settembre 2022)
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning (opens in a new tab) (Settembre 2022)
Promptagator: Few-shot Dense Retrieval From 8 Examples (opens in a new tab) (Settembre 2022)
Atlas: Few-shot Learning with Retrieval Augmented Language Models (opens in a new tab) (Novembre 2022)
DocPrompting: Generating Code by Retrieving the Docs (opens in a new tab) (Luglio 2022)
On the Advance of Making Language Models Better Reasoners (opens in a new tab) (Giugnoe 2022)
Large Language Models are Zero-Shot Reasoners (opens in a new tab) (Maggio 2022)
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations (opens in a new tab) (Maggio 2022)
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning (opens in a new tab) (Maggio 2022)
PPT: Pre-trained Prompt Tuning for Few-shot Learning (opens in a new tab) (Mqy 2022)
Toxicity Detection with Generative Prompt-based Inference (opens in a new tab) (Maggio 2022)
Learning to Transfer Prompts for Text Generation (opens in a new tab) (Maggio 2022)
The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (opens in a new tab) (Maggio 2022)
A Taxonomy of Prompt Modifiers for Text-To-Image Generation (opens in a new tab) (Aprile 2022)
PromptChainer: Chaining Large Language Model Prompts through Visual Programming (opens in a new tab) (Marzo 2022)
Self-Consistency Improves Chain of Thought Reasoning in Language Models (opens in a new tab) (Marzo 2022)
Training language models to follow instructions with human feedback (opens in a new tab)
Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? (opens in a new tab) (Febbraio 2022)
Chain of Thought Prompting Elicits Reasoning in Large Language Models (opens in a new tab) (Gennaio 2022)
Show Your Work: Scratchpads for Intermediate Computation with Language Models (opens in a new tab) (Novembre 2021)
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts (opens in a new tab) (Ottobre 2021)
Generated Knowledge Prompting for Commonsense Reasoning (opens in a new tab) (Ottobre 2021)
Multitask Prompted Training Enables Zero-Shot Task Generalization (opens in a new tab) (Ottobre 2021)
Reframing Instructional Prompts to GPTk's Language (opens in a new tab) (Settembre 2021)
Design Guidelines for Prompt Engineering Text-to-Image Generative Models (opens in a new tab) (Settembre 2021)
Making Pre-trained Language Models Better Few-shot Learners (opens in a new tab) (Agosto 2021)
Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity (opens in a new tab) (Aprile 2021)
BERTese: Learning to Speak to BERT (opens in a new tab) (Aprile 2021)
The Power of Scale for Parameter-Efficient Prompt Tuning (opens in a new tab) (Aprile 2021)
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm (opens in a new tab) (Febbraio 2021)
Calibrate Before Use: Improving Few-Shot Performance of Language Models (opens in a new tab) (Febbraio 2021)
Prefix-Tuning: Optimizing Continuous Prompts for Generation (opens in a new tab) (Gennaio 2021)
Learning to Generate Task-Specific Adapters from Task Description (opens in a new tab) (Gennaio 2021)
Making Pre-trained Language Models Better Few-shot Learners (opens in a new tab) (Dicembre 2020)
Learning from Task Descriptions (opens in a new tab) (Novembre 2020)
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts (opens in a new tab) (Ottobre 2020)
Language Models are Few-Shot Learners (opens in a new tab) (Maggio 2020)
How Can We Know What Language Models Know? (opens in a new tab) (Luglio 2020)
Scaling Laws for Neural Language Models (opens in a new tab) (Gennaio 2020)

Applicazioni

Collezioni

Pregiudizi LLM Research Findings