diff --git a/applications/Chat/evaluate/README.md b/applications/Chat/evaluate/README.md index f44311f4b..d6611abf7 100644 --- a/applications/Chat/evaluate/README.md +++ b/applications/Chat/evaluate/README.md @@ -97,7 +97,7 @@ We would like to mention that the evaluation of model answers using the GPT-3.5 ## Data Format ### Questions -The file [questions.json](./sample/questions.json) shows the example questions used to evaluate the performance of the model. The current sample questions are collected from [FastChat](https://github.com/lm-sys/FastChat/blob/main/fastchat/eval/table/question.jsonl). Each question record has the following field: +The file [questions.json](./sample/questions.json) shows the example questions used to evaluate the performance of the model. Each question record has the following field: * `id` (id, compulsory): The ID of the instruction / question. * `instruction` (str, compulsory): The instruction / question for the LLM. * `input` (str, optional): The additional context of the instruction / question. diff --git a/applications/Chat/evaluate/sample/questions.json b/applications/Chat/evaluate/sample/questions.json index cbda9c086..e9ef9f8b1 100644 --- a/applications/Chat/evaluate/sample/questions.json +++ b/applications/Chat/evaluate/sample/questions.json @@ -1,562 +1,9 @@ [ { - "category": "generic", - "instruction": "How can I improve my time management skills?", - "input": "", - "output": "", - "id": 1 - }, - { - "category": "generic", - "instruction": "What are the most effective ways to deal with stress?", - "input": "", - "output": "", - "id": 2 - }, - { - "category": "generic", - "instruction": "What are the main differences between Python and JavaScript programming languages?", - "input": "", - "output": "", - "id": 3 - }, - { - "category": "generic", - "instruction": "How can I increase my productivity while working from home?", - "input": "", - "output": "", - "id": 4 - }, - { - "category": "generic", - "instruction": "Can you explain the basics of quantum computing?", - "input": "", - "output": "", - "id": 5 - }, - { - "category": "generic", - "instruction": "What are the differences between plant-based and animal-based protein sources?", - "input": "", - "output": "", - "id": 6 - }, - { - "category": "generic", - "instruction": "How can I develop my critical thinking skills?", - "input": "", - "output": "", - "id": 7 - }, - { - "category": "generic", - "instruction": "What are the major challenges faced by the education sector today?", - "input": "", - "output": "", - "id": 8 - }, - { - "category": "generic", - "instruction": "What are the primary factors that influence consumer behavior?", - "input": "", - "output": "", - "id": 9 - }, - { - "category": "generic", - "instruction": "What are the most effective strategies for conflict resolution in the workplace?", - "input": "", - "output": "", - "id": 10 - }, - { - "category": "knowledge", - "instruction": "What are some potential implications of using a single-use plastic bottle versus a reusable bottle on both the environment and human health?", - "input": "", - "output": "", - "id": 11 - }, - { - "category": "knowledge", - "instruction": "What factors would you consider when designing an inclusive and accessible public transportation system?", - "input": "", - "output": "", - "id": 12 - }, - { - "category": "knowledge", - "instruction": "How can governments utilize fiscal and monetary policies to combat economic recessions?", - "input": "", - "output": "", - "id": 13 - }, - { - "category": "knowledge", - "instruction": "How do language and cultural barriers affect the way people communicate and form relationships in multicultural societies?", - "input": "", - "output": "", - "id": 14 - }, - { - "category": "knowledge", - "instruction": "Describe a scenario where artificial intelligence could be used to improve the quality and efficiency of healthcare delivery.", - "input": "", - "output": "", - "id": 15 - }, - { - "category": "knowledge", - "instruction": "Explain the process of gene editing using CRISPR-Cas9 technology, and discuss its potential applications and ethical implications.", - "input": "", - "output": "", - "id": 16 - }, - { - "category": "knowledge", - "instruction": "How do vaccinations work to protect individuals and communities from infectious diseases, and what is herd immunity?", - "input": "", - "output": "", - "id": 17 - }, - { - "category": "knowledge", - "instruction": "How do social media platforms influence the way people consume and share news, and what are the potential implications for the spread of misinformation?", - "input": "", - "output": "", - "id": 18 - }, - { - "category": "knowledge", - "instruction": "How do cultural, social, and economic factors influence people's food choices, and how can this knowledge be used to promote healthier diets?", - "input": "", - "output": "", - "id": 19 - }, - { - "category": "knowledge", - "instruction": "Explain the process of natural selection and how it contributes to the evolution and adaptation of species.", - "input": "", - "output": "", - "id": 20 - }, - { - "category": "roleplay", - "instruction": "How would you introduce yourself as a medieval knight at a royal banquet?", - "input": "", - "output": "", - "id": 21 - }, - { - "category": "roleplay", - "instruction": "As a pirate captain, what would you say to your crew to motivate them to search for hidden treasure?", - "input": "", - "output": "", - "id": 22 - }, - { - "category": "roleplay", - "instruction": "If you were a Shakespearean character, how would you declare your love for someone in a soliloquy?", - "input": "", - "output": "", - "id": 23 - }, - { - "category": "roleplay", - "instruction": "As a superhero, how would you explain your origin story to a curious child?", - "input": "", - "output": "", - "id": 24 - }, - { - "category": "roleplay", - "instruction": "Imagine you are a time traveler from the year 3000. What technological advancements would you tell people about?", - "input": "", - "output": "", - "id": 25 - }, - { - "category": "roleplay", - "instruction": "As a sports commentator, describe the winning play in the final seconds of a championship game.", - "input": "", - "output": "", - "id": 26 - }, - { - "category": "roleplay", - "instruction": "Pretend to be a world-famous chef. How would you describe your signature dish to a panel of judges?", - "input": "", - "output": "", - "id": 27 - }, - { - "category": "roleplay", - "instruction": "You are a mountain climber reaching the summit of Mount Everest. Describe your emotions and the view from the top.", - "input": "", - "output": "", - "id": 28 - }, - { - "category": "roleplay", - "instruction": "As a space colonist on Mars, describe your daily life and the challenges you face living on another planet.", - "input": "", - "output": "", - "id": 29 - }, - { - "category": "roleplay", - "instruction": "Pretend to be a character in a post-apocalyptic world. Describe how you survive and the allies you encounter.", - "input": "", - "output": "", - "id": 30 - }, - { - "category": "common-sense", - "instruction": "How can you determine if a restaurant is popular among locals or mainly attracts tourists, and why might this information be useful?", - "input": "", - "output": "", - "id": 31 - }, - { - "category": "common-sense", - "instruction": "What are some subtle clues that suggest someone is pretending to understand a topic or conversation when they are actually confused or uninformed?", - "input": "", - "output": "", - "id": 32 - }, - { - "category": "common-sense", - "instruction": "Why might someone choose to use a paper map or ask for directions instead of relying on a GPS device or smartphone app?", - "input": "", - "output": "", - "id": 33 - }, - { - "category": "common-sense", - "instruction": "How can you determine if a person is genuinely interested in a conversation or simply being polite?", - "input": "", - "output": "", - "id": 34 - }, - { - "category": "common-sense", - "instruction": "Why might someone prefer to shop at a small, locally-owned business instead of a large chain store, even if the prices are higher?", - "input": "", - "output": "", - "id": 35 - }, - { - "category": "common-sense", - "instruction": "How can you assess the credibility of a source of information, such as a news article or blog post, without relying solely on the reputation of the author or publisher?", - "input": "", - "output": "", - "id": 36 - }, - { - "category": "common-sense", - "instruction": "Why do some people enjoy the sensation of being scared, such as by watching horror movies or going on roller coasters, while others avoid these experiences?", - "input": "", - "output": "", - "id": 37 - }, - { - "category": "common-sense", - "instruction": "How can observing the behavior of other people in a social situation provide clues about cultural norms and expectations?", - "input": "", - "output": "", - "id": 38 - }, - { - "category": "common-sense", - "instruction": "Do we have a moral obligation to explore space, or should we focus on solving Earth's problems first?", - "input": "", - "output": "", - "id": 39 - }, - { - "category": "common-sense", - "instruction": "In a world where automation is becoming increasingly prevalent, is it more important to prioritize job creation or technological progress?", - "input": "", - "output": "", - "id": 40 - }, - { - "category": "fermi", - "instruction": "How many times does the average human blink in a lifetime? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 41 - }, - { - "category": "fermi", - "instruction": "How many atoms are in a grain of salt? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 42 - }, - { - "category": "fermi", - "instruction": "How many lightning strikes occur on Earth each day? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 43 - }, - { - "category": "fermi", - "instruction": "How many balloons would it take to lift a house like in the movie \"Up\"? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 44 - }, - { - "category": "fermi", - "instruction": "How many text messages are sent globally in a minute? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 45 - }, - { - "category": "fermi", - "instruction": "How many words are spoken daily on Earth? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 46 - }, - { - "category": "fermi", - "instruction": "How many snowflakes fall during a typical winter? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 47 - }, - { - "category": "fermi", - "instruction": "How many pages are in all the books ever written? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 48 - }, - { - "category": "fermi", - "instruction": "How many times has the Earth orbited the Sun since the beginning of life? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 49 - }, - { - "category": "fermi", - "instruction": "How many songs have been recorded throughout history? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", - "input": "", - "output": "", - "id": 50 - }, - { - "category": "counterfactual", - "instruction": "What if the Internet had been invented during the Renaissance period?", - "input": "", - "output": "", - "id": 51 - }, - { - "category": "counterfactual", - "instruction": "What if the Aztecs had successfully repelled the Spanish conquistadors?", - "input": "", - "output": "", - "id": 52 - }, - { - "category": "counterfactual", - "instruction": "What if the Black Death had not occurred in the 14th century?", - "input": "", - "output": "", - "id": 53 - }, - { - "category": "counterfactual", - "instruction": "What if Isaac Newton had focused on biology instead of physics?", - "input": "", - "output": "", - "id": 54 - }, - { - "category": "counterfactual", - "instruction": "What if the Beatles had never formed as a band?", - "input": "", - "output": "", - "id": 55 - }, - { - "category": "counterfactual", - "instruction": "What if Alan Turing had not cracked the Enigma code during World War II?", - "input": "", - "output": "", - "id": 56 - }, - { - "category": "counterfactual", - "instruction": "What if the Suez Canal had never been constructed?", - "input": "", - "output": "", - "id": 57 - }, - { - "category": "counterfactual", - "instruction": "What if the Maya civilization had never mysteriously collapsed?", - "input": "", - "output": "", - "id": 58 - }, - { - "category": "counterfactual", - "instruction": "What if Christopher Columbus had not discovered the Americas?", - "input": "", - "output": "", - "id": 59 - }, - { - "category": "counterfactual", - "instruction": "What if Vincent van Gogh had been a successful artist during his lifetime?", - "input": "", - "output": "", - "id": 60 - }, - { - "category": "coding", - "instruction": "Develop a C++ program that reads a text file line by line and counts the number of occurrences of a specific word in the file.", - "input": "", - "output": "", - "id": 61 - }, - { - "category": "coding", - "instruction": "Implement a Python function to find the longest common subsequence of two input strings using dynamic programming.", - "input": "", - "output": "", - "id": 62 - }, - { - "category": "coding", - "instruction": "Implement a regular expression in Python to validate an email address.", - "input": "", - "output": "", - "id": 63 - }, - { - "category": "coding", - "instruction": "Write a program to find the nth Fibonacci number using dynamic programming.", - "input": "", - "output": "", - "id": 64 - }, - { - "category": "coding", - "instruction": "Implement a binary search algorithm to find a specific element in a sorted array.", - "input": "", - "output": "", - "id": 65 - }, - { - "category": "coding", - "instruction": "Implement a queue data structure using two stacks in Python.", - "input": "", - "output": "", - "id": 66 - }, - { - "category": "coding", - "instruction": "Implement a program to find the common elements in two arrays without using any extra data structures.", - "input": "", - "output": "", - "id": 67 - }, - { - "category": "math", - "instruction": "Given that f(x) = 5x^3 - 2x + 3, find the value of f(2).", - "input": "", - "output": "", - "id": 68 - }, - { - "category": "math", - "instruction": "Solve for x in the equation 3x + 10 = 5(x - 2).", - "input": "", - "output": "", - "id": 69 - }, - { - "category": "math", - "instruction": "If the endpoints of a line segment are (2, -2) and (10, 4), what is the length of the segment?", - "input": "", - "output": "", - "id": 70 - }, - { - "category": "writing", - "instruction": "Can you help me write a formal email to a potential business partner proposing a joint venture?", - "input": "", - "output": "", - "id": 71 - }, - { - "category": "writing", - "instruction": "Can you help me write a resignation letter to my current employer, while leaving on good terms and expressing gratitude for the opportunities provided?", - "input": "", - "output": "", - "id": 72 - }, - { - "category": "writing", - "instruction": "Use an appropriate format to structure a formal letter of recommendation for a student applying to a prestigious graduate program in computer science.", - "input": "", - "output": "", - "id": 73 - }, - { - "category": "writing", - "instruction": "Write a compelling product launch announcement email to inform our customers of our new software solution.", - "input": "", - "output": "", - "id": 74 - }, - { - "category": "writing", - "instruction": "Draft an apology email to a customer who experienced a delay in their order, and provide reassurance that the issue has been resolved.", - "input": "", - "output": "", - "id": 75 - }, - { - "category": "writing", - "instruction": "Write a script for a YouTube video exploring the history and cultural significance of jazz.", - "input": "", - "output": "", - "id": 76 - }, - { - "category": "writing", - "instruction": "Compose an engaging travel blog post about a recent trip to Hawaii, highlighting cultural experiences and must-see attractions.", - "input": "", - "output": "", - "id": 77 - }, - { - "category": "writing", - "instruction": "Write a captivating movie review for a recently released science fiction film, discussing its plot, characters, and special effects.", - "input": "", - "output": "", - "id": 78 - }, - { - "category": "writing", - "instruction": "Structure a podcast script for an episode discussing the influence of streaming platforms on the music industry.", - "input": "", - "output": "", - "id": 79 - }, - { - "category": "writing", - "instruction": "Write a symphony concert review, discussing the orchestra's performance and overall audience experience.", - "input": "", - "output": "", - "id": 80 + "id": 0, + "instruction": "Help me summarize the following news?", + "input": "National Commercial Bank (NCB), Saudi Arabia's largest lender by assets, agreed to buy rival Samba Financial Group for $15 billion in the biggest banking takeover this year.NCB will pay 28.45 riyals ($7.58) for each Samba share, according to a statement on Sunday, valuing it at about 55.7 billion riyals. NCB will offer 0.739 new shares for each Samba share, at the lower end of the 0.736-0.787 ratio the banks set when they signed an initial framework agreement in June.The offer is a 3.5% premium to Samba's Oct. 8 closing price of 27.50 riyals and about 24% higher than the level the shares traded at before the talks were made public. Bloomberg News first reported the merger discussions.The new bank will have total assets of more than $220 billion, creating the Gulf region's third-largest lender. The entity's $46 billion market capitalization nearly matches that of Qatar National Bank QPSC, which is still the Middle East's biggest lender with about $268 billion of assets.", + "output": "NCB to pay 28.45 riyals for each Samba share. Deal will create Gulf region's third-largest lender", + "category": "closed qa" } ] \ No newline at end of file