|
|
|
|
@ -0,0 +1,158 @@
|
|
|
|
|
# 论文
|
|
|
|
|
|
|
|
|
|
以下是关于提示工程的最新论文（按发布日期排序）。我们每天更新，新论文不断涌现。我们每周将这些论文的摘要整合到上面的指南中。
|
|
|
|
|
|
|
|
|
|
## 综述
|
|
|
|
|
|
|
|
|
|
- [Augmented Language Models: a Survey](https://arxiv.org/abs/2302.07842) (Feb 2023)
|
|
|
|
|
- [A Survey for In-context Learning](https://arxiv.org/abs/2301.00234) (Dec 2022)
|
|
|
|
|
- [Towards Reasoning in Large Language Models: A Survey](https://arxiv.org/abs/2212.10403) (Dec 2022)
|
|
|
|
|
- [Reasoning with Language Model Prompting: A Survey](https://arxiv.org/abs/2212.09597) (Dec 2022)
|
|
|
|
|
- [Emergent Abilities of Large Language Models](https://arxiv.org/abs/2206.07682) (Jun 2022)
|
|
|
|
|
- [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://arxiv.org/abs/2204.13988) (Apr 2022)
|
|
|
|
|
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://arxiv.org/abs/2107.13586) (Jul 2021)
|
|
|
|
|
|
|
|
|
|
## 方法
|
|
|
|
|
|
|
|
|
|
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://arxiv.org/abs/2303.13283) (March 2023)
|
|
|
|
|
- [Fairness-guided Few-shot Prompting for Large Language Models](https://arxiv.org/abs/2303.13217) (March 2023)
|
|
|
|
|
- [Context-faithful Prompting for Large Language Models](https://arxiv.org/abs/2303.11315) (Mar 2023)
|
|
|
|
|
- [Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning](https://arxiv.org/abs/2303.10475) (Mar 2023)
|
|
|
|
|
- [UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation](https://arxiv.org/abs/2303.08518) (Mar 2023)
|
|
|
|
|
- [Model-tuning Via Prompts Makes NLP Models Adversarially Robust](https://arxiv.org/abs/2303.07320) (Mar 2023)
|
|
|
|
|
- [Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer](https://arxiv.org/abs/2303.03922) (March 2023)
|
|
|
|
|
- [CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification](https://arxiv.org/abs/2303.03628) (March 2023)
|
|
|
|
|
- [Larger language models do in-context learning differently](https://arxiv.org/abs/2303.03846) (March 2023)
|
|
|
|
|
- [OpenICL: An Open-Source Framework for In-context Learning](https://arxiv.org/abs/2303.02913) (March 2023)
|
|
|
|
|
- [Dynamic Prompting: A Unified Framework for Prompt Tuning](https://arxiv.org/abs/2303.02909) (March 2023)
|
|
|
|
|
- [Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning](https://arxiv.org/abs/2303.02861) (March 2023)
|
|
|
|
|
- [Effectiveness of Data Augmentation for Prefix Tuning with Limited Data](https://arxiv.org/abs/2303.02577) (March 2023)
|
|
|
|
|
- [Mixture of Soft Prompts for Controllable Data Generation](https://arxiv.org/abs/2303.01580) (March 2023)
|
|
|
|
|
- [Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners](https://arxiv.org/abs/2303.02151) (March 2023)
|
|
|
|
|
- [How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks](https://arxiv.org/abs/2303.00293) (March 2023)
|
|
|
|
|
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://arxiv.org/pdf/2302.10198.pdf) (Feb 2023)
|
|
|
|
|
- [EvoPrompting: Language Models for Code-Level Neural Architecture Search](https://arxiv.org/abs/2302.14838) (Feb 2023)
|
|
|
|
|
- [In-Context Instruction Learning](https://arxiv.org/abs/2302.14691) (Feb 2023)
|
|
|
|
|
- [Chain of Hindsight Aligns Language Models with Feedback](https://arxiv.org/abs/2302.02676) (Feb 2023)
|
|
|
|
|
- [Language Is Not All You Need: Aligning Perception with Language Models](https://arxiv.org/abs/2302.14045) (Feb 2023)
|
|
|
|
|
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://arxiv.org/abs/2302.12822) (Feb 2023)
|
|
|
|
|
- [Active Prompting with Chain-of-Thought for Large Language Models](https://arxiv.org/abs/2302.12246) (Feb 2023)
|
|
|
|
|
- [More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models](https://arxiv.org/abs/2302.12173) (Feb 2023)
|
|
|
|
|
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://arxiv.org/abs/2302.11382) (Feb 2023)
|
|
|
|
|
- [Guiding Large Language Models via Directional Stimulus Prompting](https://arxiv.org/abs/2302.11520) (Feb 2023)
|
|
|
|
|
- [How Does In-Context Learning Help Prompt Tuning?](https://arxiv.org/abs/2302.11521) (Feb 2023)
|
|
|
|
|
- [Scalable Prompt Generation for Semi-supervised Learning with Language Models](https://arxiv.org/abs/2302.09236) (Feb 2023)
|
|
|
|
|
- [Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints](https://arxiv.org/abs/2302.09185) (Feb 2023)
|
|
|
|
|
- [À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting](https://arxiv.org/abs/2302.07994) (Feb 2023)
|
|
|
|
|
- [GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks](https://arxiv.org/abs/2302.08043) (Feb 2023)
|
|
|
|
|
- [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
|
|
|
|
|
- [SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains](https://arxiv.org/abs/2302.06868) (Feb 2023)
|
|
|
|
|
- [Evaluating the Robustness of Discrete Prompts](https://arxiv.org/abs/2302.05619) (Feb 2023)
|
|
|
|
|
- [Compositional Exemplars for In-context Learning](https://arxiv.org/abs/2302.05698) (Feb 2023)
|
|
|
|
|
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://arxiv.org/abs/2302.03668) (Feb 2023)
|
|
|
|
|
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://arxiv.org/abs/2302.00923) (Feb 2023)
|
|
|
|
|
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://arxiv.org/abs/2302.00093) (Feb 2023)
|
|
|
|
|
- [Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models](https://arxiv.org/abs/2302.00618) (Feb 2023)
|
|
|
|
|
- [Progressive Prompts: Continual Learning for Language Models](https://arxiv.org/abs/2301.12314) (Jan 2023)
|
|
|
|
|
- [Batch Prompting: Efficient Inference with LLM APIs](https://arxiv.org/abs/2301.08721) (Jan 2023)
|
|
|
|
|
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://arxiv.org/abs/2212.14024) (Dec 2022)
|
|
|
|
|
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://arxiv.org/abs/2212.08061) (Dec 2022)
|
|
|
|
|
- [Constitutional AI: Harmlessness from AI Feedback](https://arxiv.org/abs/2212.08073) (Dec 2022)
|
|
|
|
|
- [Successive Prompting for Decomposing Complex Questions](https://arxiv.org/abs/2212.04092) (Dec 2022)
|
|
|
|
|
- [Large Language Models are reasoners with Self-Verification](https://arxiv.org/abs/2212.09561v1) (Dec 2022)
|
|
|
|
|
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://arxiv.org/abs/2212.09251) (Dec 2022)
|
|
|
|
|
- [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://arxiv.org/abs/2212.06713) (Dec 2022)
|
|
|
|
|
- [PAL: Program-aided Language Models](https://arxiv.org/abs/2211.10435) (Nov 2022)
|
|
|
|
|
- [Large Language Models Are Human-Level Prompt Engineers](https://arxiv.org/abs/2211.01910) (Nov 2022)
|
|
|
|
|
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://arxiv.org/abs/2211.09527) (Nov 2022)
|
|
|
|
|
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://arxiv.org/abs/2210.07321) (Nov 2022)
|
|
|
|
|
- [Teaching Algorithmic Reasoning via In-context Learning](https://arxiv.org/abs/2211.09066) (Nov 2022)
|
|
|
|
|
- [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://arxiv.org/abs/2211.11875) (Nov 2022)
|
|
|
|
|
- [Ask Me Anything: A simple strategy for prompting language models](https://paperswithcode.com/paper/ask-me-anything-a-simple-strategy-for) (Oct 2022)
|
|
|
|
|
- [Recitation-Augmented Language Models](https://arxiv.org/abs/2210.01296) (Oct 2022)
|
|
|
|
|
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629) (Oct 2022)
|
|
|
|
|
- [Prompting GPT-3 To Be Reliable](https://arxiv.org/abs/2210.09150) (Oct 2022)
|
|
|
|
|
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://arxiv.org/abs/2210.02406) (Oct 2022)
|
|
|
|
|
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://arxiv.org/abs/2210.01240v3) (Oct 2022)
|
|
|
|
|
- [Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples](https://arxiv.org/abs/2209.02128) (Sep 2022)
|
|
|
|
|
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://arxiv.org/abs/2209.14610) (Sep 2022)
|
|
|
|
|
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://arxiv.org/abs/2209.11755) (Sep 2022)
|
|
|
|
|
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://arxiv.org/abs/2208.03299) (Nov 2022)
|
|
|
|
|
- [DocPrompting: Generating Code by Retrieving the Docs](https://arxiv.org/abs/2207.05987) (July 2022)
|
|
|
|
|
- [On the Advance of Making Language Models Better Reasoners](https://arxiv.org/abs/2206.02336) (June 2022)
|
|
|
|
|
- [Large Language Models are Zero-Shot Reasoners](https://arxiv.org/abs/2205.11916) (May 2022)
|
|
|
|
|
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://arxiv.org/abs/2205.11822) (May 2022)
|
|
|
|
|
- [MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning](https://arxiv.org/abs/2205.00445) (May 2022)
|
|
|
|
|
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://aclanthology.org/2022.acl-long.576/) (Mqy 2022)
|
|
|
|
|
- [Toxicity Detection with Generative Prompt-based Inference](https://arxiv.org/abs/2205.12390) (May 2022)
|
|
|
|
|
- [Learning to Transfer Prompts for Text Generation](https://arxiv.org/abs/2205.01543) (May 2022)
|
|
|
|
|
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://arxiv.org/abs/2205.03401) (May 2022)
|
|
|
|
|
- [A Taxonomy of Prompt Modifiers for Text-To-Image Generation](https://arxiv.org/abs/2204.13988) (Apr 2022)
|
|
|
|
|
- [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://arxiv.org/abs/2203.06566) (Mar 2022)
|
|
|
|
|
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://arxiv.org/abs/2203.11171) (March 2022)
|
|
|
|
|
- [Training language models to follow instructions with human feedback](https://arxiv.org/abs/2203.02155)
|
|
|
|
|
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://arxiv.org/abs/2202.12837) (Feb 2022)
|
|
|
|
|
- [Chain of Thought Prompting Elicits Reasoning in Large Language Models](https://arxiv.org/abs/2201.11903) (Jan 2022)
|
|
|
|
|
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://arxiv.org/abs/2112.00114) (Nov 2021)
|
|
|
|
|
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://arxiv.org/abs/2110.01691) (Oct 2021)
|
|
|
|
|
- [Generated Knowledge Prompting for Commonsense Reasoning](https://arxiv.org/abs/2110.08387) (Oct 2021)
|
|
|
|
|
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://arxiv.org/abs/2110.08207) (Oct 2021)
|
|
|
|
|
- [Reframing Instructional Prompts to GPTk's Language](https://arxiv.org/abs/2109.07830) (Sep 2021)
|
|
|
|
|
- [Design Guidelines for Prompt Engineering Text-to-Image Generative Models](https://arxiv.org/abs/2109.06977) (Sep 2021)
|
|
|
|
|
- [Making Pre-trained Language Models Better Few-shot Learners](https://aclanthology.org/2021.acl-long.295) (Aug 2021)
|
|
|
|
|
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://arxiv.org/abs/2104.08786) (April 2021)
|
|
|
|
|
- [BERTese: Learning to Speak to BERT](https://aclanthology.org/2021.eacl-main.316) (April 2021)
|
|
|
|
|
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://arxiv.org/abs/2104.08691) (April 2021)
|
|
|
|
|
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://arxiv.org/abs/2102.07350) (Feb 2021)
|
|
|
|
|
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://arxiv.org/abs/2102.09690) (Feb 2021)
|
|
|
|
|
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://arxiv.org/abs/2101.00190) (Jan 2021)
|
|
|
|
|
- [Learning to Generate Task-Specific Adapters from Task Description](https://arxiv.org/abs/2101.00420) (Jan 2021)
|
|
|
|
|
- [Making Pre-trained Language Models Better Few-shot Learners](https://arxiv.org/abs/2012.15723) (Dec 2020)
|
|
|
|
|
- [Learning from Task Descriptions](https://aclanthology.org/2020.emnlp-main.105/) (Nov 2020)
|
|
|
|
|
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://arxiv.org/abs/2010.15980) (Oct 2020)
|
|
|
|
|
- [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165) (May 2020)
|
|
|
|
|
- [How Can We Know What Language Models Know?](https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00324/96460/How-Can-We-Know-What-Language-Models-Know) (July 2020)
|
|
|
|
|
|
|
|
|
|
## 应用
|
|
|
|
|
|
|
|
|
|
- [SPeC: A Soft Prompt-Based Calibration on Mitigating Performance Variability in Clinical Notes Summarization](https://arxiv.org/abs/2303.13035) (March 2023)
|
|
|
|
|
- [Large Language Models and Simple, Stupid Bugs](https://arxiv.org/abs/2303.11455) (March 2023)
|
|
|
|
|
- [Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?](https://arxiv.org/abs/2303.09325) (Mar 2023)
|
|
|
|
|
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://arxiv.org/abs/2303.08896) (Mar 2023)
|
|
|
|
|
- [ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction](https://arxiv.org/abs/2303.05063) (March 2023)
|
|
|
|
|
- [MathPrompter: Mathematical Reasoning using Large Language Models](https://arxiv.org/abs/2303.05398) (March 2023)
|
|
|
|
|
- [Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forums](https://arxiv.org/abs/2303.05400) (March 2023)
|
|
|
|
|
- [Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting](https://arxiv.org/abs/2303.03199) (March 2023)
|
|
|
|
|
- [Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering](https://arxiv.org/abs/2303.01903) (March 2023)
|
|
|
|
|
- [Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis](https://arxiv.org/abs/2303.00815) (March 2023)
|
|
|
|
|
- [SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks](https://arxiv.org/abs/2303.00733) (March 2023)
|
|
|
|
|
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://arxiv.org/abs/2302.14233) (Feb 2023)
|
|
|
|
|
- [Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models](https://arxiv.org/abs/2302.13439) (Feb 2023)
|
|
|
|
|
- [TabGenie: A Toolkit for Table-to-Text Generation](https://arxiv.org/abs/2302.14169) (Feb 2023)
|
|
|
|
|
- [SGL-PT: A Strong Graph Learner with Graph Prompt Tuning](https://arxiv.org/abs/2302.12449) (Feb 2023)
|
|
|
|
|
- [Few-Shot Table-to-Text Generation with Prompt-based Adapter](https://arxiv.org/abs/2302.12468) (Feb 2023)
|
|
|
|
|
- [Language Models Are Few-shot Learners for Prognostic Prediction](https://arxiv.org/abs/2302.12692) (Feb 2023)
|
|
|
|
|
- [STA: Self-controlled Text Augmentation for Improving Text Classifications](https://arxiv.org/abs/2302.12784) (Feb 2023)
|
|
|
|
|
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://arxiv.org/abs/2302.12813) (Feb 2023)
|
|
|
|
|
- [How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study](https://arxiv.org/abs/2302.10916) (Feb 2023)
|
|
|
|
|
- [Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales](https://arxiv.org/abs/2302.08961) (Feb 2023)
|
|
|
|
|
- [LabelPrompt: Effective Prompt-based Learning for Relation Classification](https://arxiv.org/abs/2302.08068) (Feb 2023)
|
|
|
|
|
- [Language Model Crossover: Variation through Few-Shot Prompting](https://arxiv.org/abs/2302.09236) (Feb 2023)
|
|
|
|
|
- [Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition](https://arxiv.org/abs/2302.08102) (Feb 2023)
|
|
|
|
|
- [The Capacity for Moral Self-Correction in Large Language Models](https://arxiv.org/abs/2302.07459) (Feb 2023)
|
|
|
|
|
- [Prompting for Multimodal Hateful Meme Classification](https://arxiv.org/abs/2302.04156) (Feb 2023)
|
|
|
|
|
- [PLACES: Prompting Language Models for Social Conversation Synthesis](https://arxiv.org/abs/2302.03269) (Feb 2023)
|
|
|
|
|
- [Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation](https://arxiv.org/abs/2302.01441) (Feb 2023)
|
|
|
|
|
- [Crawling the Internal Knowledge-Base of Language Models](https://arxiv.org/abs/2301.12810) (Jan 2023)
|
|
|
|
|
- [Legal Prompt Engineering for Multilingual Legal Judgement Prediction](https://arxiv.org/abs/2212.02199) (Dec 2022)
|
|
|
|
|
- [Investigating Prompt Engineering in Diffusion Models](https://arxiv.org/abs/2211.15462) (Nov 2022)
|
|
|
|
|
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://arxiv.org/abs/2209.09513v2) (Sep 2022)
|
|
|
|
|
- [Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language](https://arxiv.org/abs/2210.15157) (Oct 2022)
|
|
|
|
|
- [Piloting Copilot and Codex: Hot Temperature, Cold Prompts, or Black Magic?](https://arxiv.org/abs/2210.14699) (Oct 2022)
|
|
|
|
|
- [Plot Writing From Scratch Pre-Trained Language Models](https://aclanthology.org/2022.inlg-main.5) (July 2022)
|
|
|
|
|
|
|
|
|
|
## 收集
|
|
|
|
|
|
|
|
|
|
- [Chain-of-Thought Papers](https://github.com/Timothyxxx/Chain-of-ThoughtsPapers)
|
|
|
|
|
- [Papers with Code](https://paperswithcode.com/task/prompt-engineering)
|
|
|
|
|
- [Prompt Papers](https://github.com/thunlp/PromptPapers#papers)
|
Elvis Saravia
1 year ago
committed by
GitHub