diff --git a/jp-pages/_app.tsx b/jp-pages/_app.tsx
deleted file mode 100644
index 8ce13ce..0000000
--- a/jp-pages/_app.tsx
+++ /dev/null
@@ -1,23 +0,0 @@
-import type { AppProps } from 'next/app';
-import Script from 'next/script';
-import { Analytics } from '@vercel/analytics/react';
-
-function MyApp({ Component, pageProps }: AppProps) {
- return (
- <>
-
-
-
-
-
- >
- );
-}
-
-export default MyApp;
\ No newline at end of file
diff --git a/jp-pages/_meta.json b/jp-pages/_meta.json
deleted file mode 100644
index 1df29b9..0000000
--- a/jp-pages/_meta.json
+++ /dev/null
@@ -1,23 +0,0 @@
-{
- "index": "Prompt Engineering",
- "introduction": "はじめに",
- "techniques": "テクニック",
- "applications": "アプリケーション",
- "models": "モデル",
- "risks": "リスクと誤用",
- "papers": "論文",
- "tools": "ツール",
- "notebooks": "ノートブック",
- "datasets": "データセット",
- "readings": "参考文献",
- "about": {
- "title": "About",
- "type": "page"
- },
- "contact": {
- "title": "Contact ↗",
- "type": "page",
- "href": "https://twitter.com/dair_ai",
- "newWindow": true
- }
-}
diff --git a/jp-pages/models/_meta.json b/jp-pages/models/_meta.json
deleted file mode 100644
index 6f8a620..0000000
--- a/jp-pages/models/_meta.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "flan": "Flan",
- "chatgpt": "ChatGPT",
- "gpt-4": "GPT-4"
-}
-
\ No newline at end of file
diff --git a/next.config.js b/next.config.js
index 5e72a7b..b40f3c0 100644
--- a/next.config.js
+++ b/next.config.js
@@ -5,7 +5,7 @@ const withNextra = require('nextra')({
module.exports = withNextra({
i18n: {
- locales: ['en', 'zh'],
+ locales: ['en', 'zh', 'jp'],
defaultLocale: 'en'
}
})
diff --git a/pages/_meta.jp.json b/pages/_meta.jp.json
new file mode 100644
index 0000000..73d2b9b
--- /dev/null
+++ b/pages/_meta.jp.json
@@ -0,0 +1,27 @@
+{
+ "index": "Prompt Engineering",
+ "introduction": "Introduction",
+ "techniques": "Techniques",
+ "applications": "Applications",
+ "models": "Models",
+ "risks": "Risks & Misuses",
+ "papers": "Papers",
+ "tools": "Tools",
+ "notebooks": "Notebooks",
+ "datasets": "Datasets",
+ "readings": "Additional Readings",
+ "about": {
+ "title": "About",
+ "type": "page"
+ },
+ "course":{
+ "title": "Prompt Engineering Course",
+ "type": "page"
+ },
+ "contact": {
+ "title": "Contact ↗",
+ "type": "page",
+ "href": "https://twitter.com/dair_ai",
+ "newWindow": true
+ }
+}
diff --git a/jp-pages/about.mdx b/pages/about.jp.mdx
similarity index 100%
rename from jp-pages/about.mdx
rename to pages/about.jp.mdx
diff --git a/jp-pages/applications.mdx b/pages/applications.jp.mdx
similarity index 100%
rename from jp-pages/applications.mdx
rename to pages/applications.jp.mdx
diff --git a/jp-pages/applications/_meta.json b/pages/applications/_meta.jp.json
similarity index 100%
rename from jp-pages/applications/_meta.json
rename to pages/applications/_meta.jp.json
diff --git a/jp-pages/applications/generating.mdx b/pages/applications/generating.jp.mdx
similarity index 100%
rename from jp-pages/applications/generating.mdx
rename to pages/applications/generating.jp.mdx
diff --git a/jp-pages/applications/pal.mdx b/pages/applications/pal.jp.mdx
similarity index 100%
rename from jp-pages/applications/pal.mdx
rename to pages/applications/pal.jp.mdx
diff --git a/pages/course.jp.mdx b/pages/course.jp.mdx
new file mode 100644
index 0000000..7680f81
--- /dev/null
+++ b/pages/course.jp.mdx
@@ -0,0 +1,11 @@
+# Prompt Engineering Course
+
+We have partnered with Sphere to deliver a ["Prompting Engineering for LLMs"](https://www.getsphere.com/cohorts/prompt-engineering-for-llms?source=promptingguide) course in May, 2023.
+
+This hands-on course is designed to teach all the latest prompt engineering techniques and tools used in the real-world for effectively building applications of top of large language models.
+
+If you want to take your prompt engineering skills to the next level, we highly recommend the course.
+
+This course also includes a certificate of completion.
+
+Note that this course will be delivered in English.
\ No newline at end of file
diff --git a/jp-pages/datasets.mdx b/pages/datasets.jp.mdx
similarity index 100%
rename from jp-pages/datasets.mdx
rename to pages/datasets.jp.mdx
diff --git a/jp-pages/index.mdx b/pages/index.jp.mdx
similarity index 100%
rename from jp-pages/index.mdx
rename to pages/index.jp.mdx
diff --git a/jp-pages/introduction.mdx b/pages/introduction.jp.mdx
similarity index 100%
rename from jp-pages/introduction.mdx
rename to pages/introduction.jp.mdx
diff --git a/jp-pages/introduction/_meta.json b/pages/introduction/_meta.jp.json
similarity index 100%
rename from jp-pages/introduction/_meta.json
rename to pages/introduction/_meta.jp.json
diff --git a/jp-pages/introduction/basics.mdx b/pages/introduction/basics.jp.mdx
similarity index 100%
rename from jp-pages/introduction/basics.mdx
rename to pages/introduction/basics.jp.mdx
diff --git a/jp-pages/introduction/elements.mdx b/pages/introduction/elements.jp.mdx
similarity index 100%
rename from jp-pages/introduction/elements.mdx
rename to pages/introduction/elements.jp.mdx
diff --git a/jp-pages/introduction/examples.mdx b/pages/introduction/examples.jp.mdx
similarity index 100%
rename from jp-pages/introduction/examples.mdx
rename to pages/introduction/examples.jp.mdx
diff --git a/jp-pages/introduction/settings.mdx b/pages/introduction/settings.jp.mdx
similarity index 100%
rename from jp-pages/introduction/settings.mdx
rename to pages/introduction/settings.jp.mdx
diff --git a/jp-pages/introduction/tips.mdx b/pages/introduction/tips.jp.mdx
similarity index 100%
rename from jp-pages/introduction/tips.mdx
rename to pages/introduction/tips.jp.mdx
diff --git a/jp-pages/models.mdx b/pages/models.jp.mdx
similarity index 100%
rename from jp-pages/models.mdx
rename to pages/models.jp.mdx
diff --git a/pages/models/_meta.jp.json b/pages/models/_meta.jp.json
new file mode 100644
index 0000000..a449f46
--- /dev/null
+++ b/pages/models/_meta.jp.json
@@ -0,0 +1,8 @@
+{
+ "flan": "Flan",
+ "chatgpt": "ChatGPT",
+ "llama": "LLaMA",
+ "gpt-4": "GPT-4",
+ "collection": "Model Collection"
+}
+
\ No newline at end of file
diff --git a/pages/models/_meta.zh.json b/pages/models/_meta.zh.json
index a449f46..0ad55fb 100644
--- a/pages/models/_meta.zh.json
+++ b/pages/models/_meta.zh.json
@@ -5,4 +5,5 @@
"gpt-4": "GPT-4",
"collection": "Model Collection"
}
+
\ No newline at end of file
diff --git a/jp-pages/models/chatgpt.mdx b/pages/models/chatgpt.jp.mdx
similarity index 100%
rename from jp-pages/models/chatgpt.mdx
rename to pages/models/chatgpt.jp.mdx
diff --git a/pages/models/collection.jp.mdx b/pages/models/collection.jp.mdx
new file mode 100644
index 0000000..0e5b99d
--- /dev/null
+++ b/pages/models/collection.jp.mdx
@@ -0,0 +1,64 @@
+# Model Collection
+
+import { Callout, FileTree } from 'nextra-theme-docs'
+
+
+ This section is under heavy development.
+
+
+This section consists of a collection and summary of notable and foundational LLMs. (Data adopted from [Papers with Code](https://paperswithcode.com/methods/category/language-models) and the recent work by [Zhao et al. (2023)](https://arxiv.org/pdf/2303.18223.pdf).
+
+## Models
+
+| Model | Release Date | Description |
+| --- | --- | --- |
+| [BERT](https://arxiv.org/abs/1810.04805)| 2018 | Bidirectional Encoder Representations from Transformers |
+| [GPT](https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/language-unsupervised/language_understanding_paper.pdf) | 2018 | Improving Language Understanding by Generative Pre-Training |
+| [RoBERTa](https://arxiv.org/abs/1907.11692) | 2019 | A Robustly Optimized BERT Pretraining Approach |
+| [GPT-2](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) | 2019 | Language Models are Unsupervised Multitask Learners |
+| [T5](https://arxiv.org/abs/1910.10683) | 2019 | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer |
+| [BART](https://arxiv.org/abs/1910.13461) | 2019 | Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |
+| [ALBERT](https://arxiv.org/abs/1909.11942) |2019 | A Lite BERT for Self-supervised Learning of Language Representations |
+| [XLNet](https://arxiv.org/abs/1906.08237) | 2019 | Generalized Autoregressive Pretraining for Language Understanding and Generation |
+| [CTRL](https://arxiv.org/abs/1909.05858) |2019 | CTRL: A Conditional Transformer Language Model for Controllable Generation |
+| [ERNIE](https://arxiv.org/abs/1904.09223v1) | 2019| ERNIE: Enhanced Representation through Knowledge Integration |
+| [GShard](https://arxiv.org/abs/2006.16668v1) | 2020 | GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding |
+| [GPT-3](https://arxiv.org/abs/2005.14165) | 2020 | Language Models are Few-Shot Learners |
+| [LaMDA](https://arxiv.org/abs/2201.08239v3) | 2021 | LaMDA: Language Models for Dialog Applications |
+| [PanGu-α](https://arxiv.org/abs/2104.12369v1) | 2021 | PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation |
+| [mT5](https://arxiv.org/abs/2010.11934v3) | 2021 | mT5: A massively multilingual pre-trained text-to-text transformer |
+| [CPM-2](https://arxiv.org/abs/2106.10715v3) | 2021 | CPM-2: Large-scale Cost-effective Pre-trained Language Models |
+| [T0](https://arxiv.org/abs/2110.08207) |2021 |Multitask Prompted Training Enables Zero-Shot Task Generalization |
+| [HyperCLOVA](https://arxiv.org/abs/2109.04650) | 2021 | What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers |
+| [Codex](https://arxiv.org/abs/2107.03374v2) |2021 |Evaluating Large Language Models Trained on Code |
+| [ERNIE 3.0](https://arxiv.org/abs/2107.02137v1) | 2021 | ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation|
+| [Jurassic-1](https://uploads-ssl.webflow.com/60fd4503684b466578c0d307/61138924626a6981ee09caf6_jurassic_tech_paper.pdf) | 2021 | Jurassic-1: Technical Details and Evaluation |
+| [FLAN](https://arxiv.org/abs/2109.01652v5) | 2021 | Finetuned Language Models Are Zero-Shot Learners |
+| [MT-NLG](https://arxiv.org/abs/2201.11990v3) | 2021 | Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model|
+| [Yuan 1.0](https://arxiv.org/abs/2110.04725v2) | 2021| Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning |
+| [WebGPT](https://arxiv.org/abs/2112.09332v3) | 2021 | WebGPT: Browser-assisted question-answering with human feedback |
+| [Gopher](https://arxiv.org/abs/2112.11446v2) |2021 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
+| [ERNIE 3.0 Titan](https://arxiv.org/abs/2112.12731v1) |2021 | ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation |
+| [GLaM](https://arxiv.org/abs/2112.06905) | 2021 | GLaM: Efficient Scaling of Language Models with Mixture-of-Experts |
+| [InstructGPT](https://arxiv.org/abs/2203.02155v1) | 2022 | Training language models to follow instructions with human feedback |
+| [GPT-NeoX-20B](https://arxiv.org/abs/2204.06745v1) | 2022 | GPT-NeoX-20B: An Open-Source Autoregressive Language Model |
+| [AlphaCode](https://arxiv.org/abs/2203.07814v1) | 2022 | Competition-Level Code Generation with AlphaCode |
+| [CodeGen](https://arxiv.org/abs/2203.13474v5) | 2022 | CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis |
+| [Chinchilla](https://arxiv.org/abs/2203.15556) | 2022 | Shows that for a compute budget, the best performances are not achieved by the largest models but by smaller models trained on more data. |
+| [Tk-Instruct](https://arxiv.org/abs/2204.07705v3) | 2022 | Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks |
+| [UL2](https://arxiv.org/abs/2205.05131v3) | 2022 | UL2: Unifying Language Learning Paradigms |
+| [PaLM](https://arxiv.org/abs/2204.02311v5) |2022| PaLM: Scaling Language Modeling with Pathways |
+| [OPT](https://arxiv.org/abs/2205.01068) | 2022 | OPT: Open Pre-trained Transformer Language Models |
+| [BLOOM](https://arxiv.org/abs/2211.05100v3) | 2022 | BLOOM: A 176B-Parameter Open-Access Multilingual Language Model |
+| [GLM-130B](https://arxiv.org/abs/2210.02414v1) | 2022 | GLM-130B: An Open Bilingual Pre-trained Model |
+| [AlexaTM](https://arxiv.org/abs/2208.01448v2) | 2022 | AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model |
+| [Flan-T5](https://arxiv.org/abs/2210.11416v5) | 2022 | Scaling Instruction-Finetuned Language Models |
+| [Sparrow](https://arxiv.org/abs/2209.14375) | 2022 | Improving alignment of dialogue agents via targeted human judgements |
+| [U-PaLM](https://arxiv.org/abs/2210.11399v2) | 2022 | Transcending Scaling Laws with 0.1% Extra Compute |
+| [mT0](https://arxiv.org/abs/2211.01786v1) | 2022 | Crosslingual Generalization through Multitask Finetuning |
+| [Galactica](https://arxiv.org/abs/2211.09085v1) | 2022 | Galactica: A Large Language Model for Science |
+| [OPT-IML](https://arxiv.org/abs/2212.12017v3) | 2022 | OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization |
+| [LLaMA](https://arxiv.org/abs/2302.13971v1) | 2023 | LLaMA: Open and Efficient Foundation Language Models |
+| [GPT-4](https://arxiv.org/abs/2303.08774v3) | 2023 |GPT-4 Technical Report |
+| [PanGu-Σ](https://arxiv.org/abs/2303.10845v1) | 2023 | PanGu-Σ: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing |
+| [BloombergGPT](https://arxiv.org/abs/2303.17564v1)| 2023 |BloombergGPT: A Large Language Model for Finance|
\ No newline at end of file
diff --git a/jp-pages/models/flan.mdx b/pages/models/flan.jp.mdx
similarity index 100%
rename from jp-pages/models/flan.mdx
rename to pages/models/flan.jp.mdx
diff --git a/jp-pages/models/gpt-4.mdx b/pages/models/gpt-4.jp.mdx
similarity index 100%
rename from jp-pages/models/gpt-4.mdx
rename to pages/models/gpt-4.jp.mdx
diff --git a/pages/models/llama.jp.mdx b/pages/models/llama.jp.mdx
new file mode 100644
index 0000000..51cdc09
--- /dev/null
+++ b/pages/models/llama.jp.mdx
@@ -0,0 +1,3 @@
+# LLaMA: Open and Efficient Foundation Language Models
+
+Needs translation! Feel free to contribute a translating by clicking the `Edit this page` button on the right side.
\ No newline at end of file
diff --git a/jp-pages/notebooks.mdx b/pages/notebooks.jp.mdx
similarity index 100%
rename from jp-pages/notebooks.mdx
rename to pages/notebooks.jp.mdx
diff --git a/jp-pages/papers.mdx b/pages/papers.jp.mdx
similarity index 87%
rename from jp-pages/papers.mdx
rename to pages/papers.jp.mdx
index e86c5a6..470f31a 100644
--- a/jp-pages/papers.mdx
+++ b/pages/papers.jp.mdx
@@ -4,6 +4,7 @@
## 概要
+ - [Nature Language Reasoning, A Survey](https://arxiv.org/abs/2303.14725) (March 2023)
- [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)
@@ -14,6 +15,10 @@
## 取り組み
+ - [Self-Refine: Iterative Refinement with Self-Feedback](https://arxiv.org/abs/2303.17651v1) (Mar 2023)
+ - [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://arxiv.org/abs/2303.13824) (Mar 2023)
+ - [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://arxiv.org/abs/2303.13283) (Mar 2023)
+ - [Fairness-guided Few-shot Prompting for Large Language Models](https://arxiv.org/abs/2303.13217) (Mar 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)
@@ -110,9 +115,22 @@
- [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)
+ - [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361) (Jan 2020)
## Applications
+ - [BloombergGPT: A Large Language Model for Finance](https://arxiv.org/abs/2303.17564) (March 2023)
+ - [Medical Intervention Duration Estimation Using Language-enhanced Transformer Encoder with Medical Prompts](https://arxiv.org/abs/2303.17408) (March 2023)
+ - [Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes](https://arxiv.org/abs/2303.15846) (March 2023)
+ - [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://arxiv.org/abs/2303.16434) (March 2023)
+ - [Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning](https://arxiv.org/abs/2303.16445) (March 2023)
+ - [Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses](https://arxiv.org/abs/2303.15587) (March 2023)
+ - [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://arxiv.org/abs/2303.14375) (March 2023)
+ - [Debiasing Scores and Prompts of 2D Diffusion for Robust Text-to-3D Generation](https://arxiv.org/abs/2303.15413) (March 2023)
+ - [Zero-shot Model Diagnosis](https://arxiv.org/abs/2303.15441#) (March 2023)
+ - [Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages](https://arxiv.org/abs/2303.13592) (March 2023)
+ - [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)
@@ -146,6 +164,7 @@
- [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)
+ - [Survey of Hallucination in Natural Language Generation](https://arxiv.org/abs/2202.03629) (Feb 2022)
## Collections
diff --git a/pages/papers.zh.mdx b/pages/papers.zh.mdx
index d6b4314..c21506a 100644
--- a/pages/papers.zh.mdx
+++ b/pages/papers.zh.mdx
@@ -4,6 +4,7 @@
## 综述
+ - [Nature Language Reasoning, A Survey](https://arxiv.org/abs/2303.14725) (March 2023)
- [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)
@@ -14,8 +15,10 @@
## 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)
+ - [Self-Refine: Iterative Refinement with Self-Feedback](https://arxiv.org/abs/2303.17651v1) (Mar 2023)
+ - [kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference](https://arxiv.org/abs/2303.13824) (Mar 2023)
+ - [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://arxiv.org/abs/2303.13283) (Mar 2023)
+ - [Fairness-guided Few-shot Prompting for Large Language Models](https://arxiv.org/abs/2303.13217) (Mar 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)
@@ -112,9 +115,20 @@
- [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)
+ - [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361) (Jan 2020)
## 应用
+ - [BloombergGPT: A Large Language Model for Finance](https://arxiv.org/abs/2303.17564) (March 2023)
+ - [Medical Intervention Duration Estimation Using Language-enhanced Transformer Encoder with Medical Prompts](https://arxiv.org/abs/2303.17408) (March 2023)
+ - [Soft-prompt tuning to predict lung cancer using primary care free-text Dutch medical notes](https://arxiv.org/abs/2303.15846) (March 2023)
+ - [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://arxiv.org/abs/2303.16434) (March 2023)
+ - [Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning](https://arxiv.org/abs/2303.16445) (March 2023)
+ - [Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses](https://arxiv.org/abs/2303.15587) (March 2023)
+ - [Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning](https://arxiv.org/abs/2303.14375) (March 2023)
+ - [Debiasing Scores and Prompts of 2D Diffusion for Robust Text-to-3D Generation](https://arxiv.org/abs/2303.15413) (March 2023)
+ - [Zero-shot Model Diagnosis](https://arxiv.org/abs/2303.15441#) (March 2023)
+ - [Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages](https://arxiv.org/abs/2303.13592) (March 2023)
- [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)
@@ -150,7 +164,7 @@
- [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)
-
+ - [Survey of Hallucination in Natural Language Generation](https://arxiv.org/abs/2202.03629) (Feb 2022)
## 收集
- [Chain-of-Thought Papers](https://github.com/Timothyxxx/Chain-of-ThoughtsPapers)
diff --git a/jp-pages/readings.mdx b/pages/readings.jp.mdx
similarity index 100%
rename from jp-pages/readings.mdx
rename to pages/readings.jp.mdx
diff --git a/jp-pages/risks.mdx b/pages/risks.jp.mdx
similarity index 100%
rename from jp-pages/risks.mdx
rename to pages/risks.jp.mdx
diff --git a/jp-pages/risks/_meta.json b/pages/risks/_meta.jp.json
similarity index 100%
rename from jp-pages/risks/_meta.json
rename to pages/risks/_meta.jp.json
diff --git a/jp-pages/risks/adversarial.mdx b/pages/risks/adversarial.jp.mdx
similarity index 100%
rename from jp-pages/risks/adversarial.mdx
rename to pages/risks/adversarial.jp.mdx
diff --git a/jp-pages/risks/biases.mdx b/pages/risks/biases.jp.mdx
similarity index 100%
rename from jp-pages/risks/biases.mdx
rename to pages/risks/biases.jp.mdx
diff --git a/jp-pages/risks/factuality.mdx b/pages/risks/factuality.jp.mdx
similarity index 100%
rename from jp-pages/risks/factuality.mdx
rename to pages/risks/factuality.jp.mdx
diff --git a/jp-pages/techniques.mdx b/pages/techniques.jp.mdx
similarity index 100%
rename from jp-pages/techniques.mdx
rename to pages/techniques.jp.mdx
diff --git a/jp-pages/techniques/_meta.json b/pages/techniques/_meta.jp.json
similarity index 100%
rename from jp-pages/techniques/_meta.json
rename to pages/techniques/_meta.jp.json
diff --git a/jp-pages/techniques/activeprompt.mdx b/pages/techniques/activeprompt.jp.mdx
similarity index 100%
rename from jp-pages/techniques/activeprompt.mdx
rename to pages/techniques/activeprompt.jp.mdx
diff --git a/jp-pages/techniques/ape.mdx b/pages/techniques/ape.jp.mdx
similarity index 100%
rename from jp-pages/techniques/ape.mdx
rename to pages/techniques/ape.jp.mdx
diff --git a/jp-pages/techniques/consistency.mdx b/pages/techniques/consistency.jp.mdx
similarity index 100%
rename from jp-pages/techniques/consistency.mdx
rename to pages/techniques/consistency.jp.mdx
diff --git a/jp-pages/techniques/cot.mdx b/pages/techniques/cot.jp.mdx
similarity index 100%
rename from jp-pages/techniques/cot.mdx
rename to pages/techniques/cot.jp.mdx
diff --git a/jp-pages/techniques/dsp.mdx b/pages/techniques/dsp.jp.mdx
similarity index 100%
rename from jp-pages/techniques/dsp.mdx
rename to pages/techniques/dsp.jp.mdx
diff --git a/jp-pages/techniques/fewshot.mdx b/pages/techniques/fewshot.jp.mdx
similarity index 100%
rename from jp-pages/techniques/fewshot.mdx
rename to pages/techniques/fewshot.jp.mdx
diff --git a/jp-pages/techniques/graph.mdx b/pages/techniques/graph.jp.mdx
similarity index 100%
rename from jp-pages/techniques/graph.mdx
rename to pages/techniques/graph.jp.mdx
diff --git a/jp-pages/techniques/knowledge.mdx b/pages/techniques/knowledge.jp.mdx
similarity index 100%
rename from jp-pages/techniques/knowledge.mdx
rename to pages/techniques/knowledge.jp.mdx
diff --git a/jp-pages/techniques/multimodalcot.mdx b/pages/techniques/multimodalcot.jp.mdx
similarity index 100%
rename from jp-pages/techniques/multimodalcot.mdx
rename to pages/techniques/multimodalcot.jp.mdx
diff --git a/jp-pages/techniques/react.mdx b/pages/techniques/react.jp.mdx
similarity index 100%
rename from jp-pages/techniques/react.mdx
rename to pages/techniques/react.jp.mdx
diff --git a/jp-pages/techniques/zeroshot.mdx b/pages/techniques/zeroshot.jp.mdx
similarity index 100%
rename from jp-pages/techniques/zeroshot.mdx
rename to pages/techniques/zeroshot.jp.mdx
diff --git a/jp-pages/tools.mdx b/pages/tools.jp.mdx
similarity index 100%
rename from jp-pages/tools.mdx
rename to pages/tools.jp.mdx
diff --git a/theme.config.tsx b/theme.config.tsx
index c25e3ed..5d4a152 100644
--- a/theme.config.tsx
+++ b/theme.config.tsx
@@ -17,7 +17,8 @@ const config: DocsThemeConfig = {
),
i18n: [
{ locale: 'en', text: 'English' },
- { locale: 'zh', text: '中文' }
+ { locale: 'zh', text: '中文' },
+ { locale: 'jp', text: '日本語'}
],
head: function UseHead() {
const { title } = useConfig()