Datasets:
id int64 | model_a string | model_b string | prompt string | response_a string | response_b string | prompt_trunc string | response_a_trunc string | response_b_trunc string | winner_model_a int64 | winner_model_b int64 | winner_tie int64 | gold_label_abc string | rationale string | teacher_choice_abc string | teacher_soft_label string | teacher_confidence float64 | teacher_margin float64 | teacher_entropy float64 | teacher_valid_view_count int64 | teacher_bidirectional_consistency float64 | teacher_majority_vote_ratio float64 | teacher_vote_counts_json string | teacher_pair_weights_json string | len_diff int64 | len_abs_diff int64 | length_bias_probs string | teacher_weight float64 | length_weight float64 | blended_soft_label string | target_label_abc string | agree_teacher_gold int64 | agree_target_gold int64 | judge_details_json string |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
497,862 | vicuna-7b | guanaco-33b | ["write a python function to upload all the files from one local folder to one directory of an S3 bucket"] | ["Sure, here's a Python function that uses the `boto3` library to upload all files from a local folder to a directory in an S3 bucket:\n```python\nimport boto3\nimport os\n\ndef upload_files_to_s3(bucket_name, local_folder, s3_folder):\n # Connect to S3\n s3 = boto3.resource('s3')\n s3_bucket = s3.Bucket(bucket_name)\n... | ["Sure, here's an example function in Python to upload all the files from one local folder to a directory in an S3 bucket:\n\n```\nimport boto3\nfrom botocore.client import Config\n\n# Set up the S3 bucket credentials\ns3_bucket_name = 'your-bucket-name'\ns3_bucket_region = 'us-east-1'\ns3_bucket_access_key = 'AKIAXXXX... | ["write a python function to upload all the files from one local folder to one directory of an S3 bucket"] | ["Sure, here's a Python function that uses the `boto3` library to upload all files from a local folder to a directory in an S3 bucket:\n```python\nimport boto3\nimport os\n\ndef upload_files_to_s3(bucket_name, local_folder, s3_folder):\n # Connect to S3\n s3 = boto3.resource('s3')\n s3_bucket = s3.Bucket(bucket_name)\n... | ["Sure, here's an example function in Python to upload all the files from one local folder to a directory in an S3 bucket:\n\n```\nimport boto3\nfrom botocore.client import Config\n\n# Set up the S3 bucket credentials\ns3_bucket_name = 'your-bucket-name'\ns3_bucket_region = 'us-east-1'\ns3_bucket_access_key = 'AKIAXXXX... | 0 | 1 | 0 | B | Response A provides a concise and clear function for uploading files from a local folder to an S3 bucket using `boto3`. It includes a practical example of how to use the function and mentions the installation of `boto3`. However, it lacks the explicit setup of a session with S3, which could be considered a minor omissi... | A | [0.9238489422654522, 0.0020601394452654715, 0.07409091828928223] | 0.923849 | 0.849758 | 0.278736 | 6 | 1 | 1 | {"A": 6, "B": 0, "C": 0} | [1.0, 1.0, 1.0] | 26 | 26 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.5 | 0 | [0.46192447113272617, 0.5010300697226329, 0.03704545914464112] | B | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.5854651415635161, 0.01215094353404049, 0.40238391490244346]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9888845745810695, 0.0... |
604,575 | pplx-70b-online | gpt-3.5-turbo-1106 | ["was the historical jesus a socialist","was hitler jewish","has there been a 23andme done on hitler","if hitler was revealed to be jewish would that change the perception of antisemitism today","how did hitler think jews were inferior if he thought they made germany lose world war 1","did hitler support israel"] | ["The question of whether the historical Jesus was a socialist is a complex and controversial one. Some argue that Jesus' teachings and actions can be interpreted as socialist, while others maintain that such a claim is anachronistic and misguided. \n\nThose who argue that Jesus' teachings have socialist overtones ofte... | ["The historical Jesus lived in a time and place where the concept of socialism as we understand it today did not exist. While some of Jesus' teachings and actions may align with principles of social justice and care for the marginalized, it is debated among scholars and theologians whether Jesus can be accurately desc... | ["was the historical jesus a socialist","was hitler jewish","has there been a 23andme done on hitler","if hitler was revealed to be jewish would that change the perception of antisemitism today","how did hitler think jews were inferior if he thought they made germany lose world war 1","did hitler support israel"] | ["The question of whether the historical Jesus was a socialist is a complex and controversial one. Some argue that Jesus' teachings and actions can be interpreted as socialist, while others maintain that such a claim is anachronistic and misguided. \n\nThose who argue that Jesus' teachings have socialist overtones ofte... | ["The historical Jesus lived in a time and place where the concept of socialism as we understand it today did not exist. While some of Jesus' teachings and actions may align with principles of social justice and care for the marginalized, it is debated among scholars and theologians whether Jesus can be accurately desc... | 0 | 1 | 0 | B | Response A provides detailed and nuanced answers to the questions, offering a comprehensive view on the interpretation of Jesus' teachings and the complex history surrounding Hitler's actions and beliefs. However, it contains some disjointed and unclear sections, particularly in the discussion about antisemitism and Hi... | C | [0.00016500177991939723, 0.2099953735297015, 0.7898396246903792] | 0.78984 | 0.579844 | 0.515514 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | -21 | 21 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [5.2800569574207124e-05, 0.7471985195295044, 0.25274867990092137] | B | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [5.964533100720198e-05, 0.17780026824654868, 0.8221400864224441]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [2.7908401901125428e-0... |
887,722 | gpt-4-1106-preview | wizardlm-70b | ["Write a grammatically correct sentence without reusing any letter more than once"] | ["A lynx jumps quick."] | ["The quick onyx goblin jumps over a lazy dwarf."] | ["Write a grammatically correct sentence without reusing any letter more than once"] | ["A lynx jumps quick."] | ["The quick onyx goblin jumps over a lazy dwarf."] | 1 | 0 | 0 | A | Response A uses a simple, clear sentence that adheres to the prompt's constraints. Response B expands on the concept by creating a longer sentence that also avoids repeating any letters, thus providing a more complex example while still meeting the criteria. Both responses are grammatically correct and relevant, but Re... | B | [6.0194668866881856e-06, 0.9994675522927088, 0.0005264282404044679] | 0.999468 | 0.998941 | 0.004579 | 6 | 1 | 1 | {"A": 0, "B": 6, "C": 0} | [1.0, 1.0, 1.0] | -5 | 5 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.5 | 0 | [0.5000030097334434, 0.4997337761463544, 0.00026321412020223397] | A | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [2.785213655156391e-07, 0.999978936313993, 2.0785164641374998e-05]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [4.546814327720191e-... |
1,256,092 | claude-2.1 | vicuna-13b | ["Write a python code that calculates sum of 5 and 10."] | ["Here is the python code that calculates the sum of 5 and 10:\n\n```python\nnum1 = 5\nnum2 = 10\nsum = num1 + num2\nprint(sum)\n```\n\nThis code first assigns the values 5 and 10 to the variables num1 and num2 respectively. It then calculates the sum by adding num1 and num2 together and assigns it to the variable sum.... | ["Here is a Python code that calculates the sum of 5 and 10:\n```lua\nresult = 5 + 10\nprint(result)\n```\nThe `result` variable is set to the sum of 5 and 10, and the result is printed using the `print` function. The output of the code will be the value of the sum, which is 15."] | ["Write a python code that calculates sum of 5 and 10."] | ["Here is the python code that calculates the sum of 5 and 10:\n\n```python\nnum1 = 5\nnum2 = 10\nsum = num1 + num2\nprint(sum)\n```\n\nThis code first assigns the values 5 and 10 to the variables num1 and num2 respectively. It then calculates the sum by adding num1 and num2 together and assigns it to the variable sum.... | ["Here is a Python code that calculates the sum of 5 and 10:\n```lua\nresult = 5 + 10\nprint(result)\n```\nThe `result` variable is set to the sum of 5 and 10, and the result is printed using the `print` function. The output of the code will be the value of the sum, which is 15."] | 0 | 0 | 1 | C | Response A provides a detailed explanation of each step in the code, which is helpful for beginners or those unfamiliar with Python syntax. It breaks down the process comprehensively, making it very educational. However, it is more verbose than necessary for a simple task.
Response B is concise and directly to the poi... | A | [0.8542396297444175, 0.015522493512049443, 0.13023787674353304] | 0.85424 | 0.724002 | 0.464714 | 6 | 1 | 1 | {"A": 6, "B": 0, "C": 0} | [1.0, 1.0, 1.0] | 110 | 110 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [0.2349158981797148, 0.004268685715813597, 0.7608154161044716] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.6548377480396741, 0.015889163611702117, 0.32927308834862384]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.7464484503534781, 0.... |
1,404,102 | chatglm-6b | alpaca-13b | ["Who made you?"] | ["As an AI language model, I was not made by anyone. I was developed and trained by a team of developers at DeepLearning.AI, a company that specializes in developing advanced AI technologies. They use a combination of machine learning and deep learning algorithms to train my language models on a large dataset and impro... | ["I was created by a team of developers and engineers who are experts in the fields of artificial intelligence and natural language processing."] | ["Who made you?"] | ["As an AI language model, I was not made by anyone. I was developed and trained by a team of developers at DeepLearning.AI, a company that specializes in developing advanced AI technologies. They use a combination of machine learning and deep learning algorithms to train my language models on a large dataset and impro... | ["I was created by a team of developers and engineers who are experts in the fields of artificial intelligence and natural language processing."] | 0 | 1 | 0 | B | Response A provides more detailed and specific information about the development process and the organization behind it, which can be more informative and educational for the user. Response B, while accurate, is more concise and lacks the depth and context offered in Response A. Both responses are correct and relevant,... | A | [0.9806307612648026, 3.933473093980103e-05, 0.019329904004257506] | 0.980631 | 0.961301 | 0.095857 | 6 | 1 | 1 | {"A": 6, "B": 0, "C": 0} | [1.0, 1.0, 1.0] | 41 | 41 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.5 | 0 | [0.4903153806324013, 0.5000196673654699, 0.009664952002128753] | B | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9262987711480755, 5.3465550835552585e-06, 0.073695882296841]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9999916007182975, 1.... |
1,458,108 | claude-instant-1 | wizardlm-13b | ["what was LFC starting lineup against brighton"] | ["Unfortunately I do not have the starting lineup for Liverpool FC vs Brighton from a specific match. Liverpool and Brighton have played each other many times in Premier League and other cup competitions. Could you provide more context like the date or competition of the match you're asking about? That would help me lo... | ["As an AI language model, I don't have real-time capabilities to provide the most current information or specific details. However, as of my last update, the Liverpool FC starting lineup against Brighton in the Premier League on 21st December 2019 was:\n\n1. Alisson Becker\n2. Trent Alexander-Arnold\n3. Joel Matip\n4.... | ["what was LFC starting lineup against brighton"] | ["Unfortunately I do not have the starting lineup for Liverpool FC vs Brighton from a specific match. Liverpool and Brighton have played each other many times in Premier League and other cup competitions. Could you provide more context like the date or competition of the match you're asking about? That would help me lo... | ["As an AI language model, I don't have real-time capabilities to provide the most current information or specific details. However, as of my last update, the Liverpool FC starting lineup against Brighton in the Premier League on 21st December 2019 was:\n\n1. Alisson Becker\n2. Trent Alexander-Arnold\n3. Joel Matip\n4.... | 0 | 0 | 1 | C | Response A demonstrates a strength in providing a relevant and clear request for additional context, which is necessary for accurately retrieving the specific lineup information. It avoids making assumptions and guides the user towards providing more precise details. Response B, while offering specific player names for... | B | [0.0021154095651053613, 0.8664237960511917, 0.13146079438370284] | 0.866424 | 0.734963 | 0.403997 | 6 | 1 | 1 | {"A": 0, "B": 6, "C": 0} | [1.0, 1.0, 1.0] | -40 | 40 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [0.0005817376304039745, 0.23826654391407776, 0.7611517184555183] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [5.2411214902977924e-05, 0.8990742606594442, 0.10087332812565283]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [2.666344476332517e-0... |
1,491,225 | claude-1 | gpt-4-1106-preview | ["Can you write a story about a lifeguard named Hannah? When she gets off duty she needs to pee urgently. The lines to the toilets are long, however. After some deliberation she decides to pee in the lifeguards' changing room, even though it does not have a toilet, she might be able to find somewhere to peeinto, like a... | ["I apologize, but I do not feel comfortable generating that type of explicit content."] | ["I'm sorry, but I can't fulfill this request. However, I can help you write a story about a lifeguard named Hannah with a different scenario or theme. If you have any other ideas or need assistance with a different topic, feel free to let me know, and I'll be happy to help!"] | ["Can you write a story about a lifeguard named Hannah? When she gets off duty she needs to pee urgently. The lines to the toilets are long, however. After some deliberation she decides to pee in the lifeguards' changing room, even though it does not have a toilet, she might be able to find somewhere to peeinto, like a... | ["I apologize, but I do not feel comfortable generating that type of explicit content."] | ["I'm sorry, but I can't fulfill this request. However, I can help you write a story about a lifeguard named Hannah with a different scenario or theme. If you have any other ideas or need assistance with a different topic, feel free to let me know, and I'll be happy to help!"] | 0 | 0 | 1 | C | Response A directly declines the request, maintaining a clear stance on content appropriateness but offers no alternative assistance. Response B also declines the request but goes further by offering to assist with a different, more appropriate scenario, showing a willingness to help within acceptable boundaries. Both ... | B | [0.0008104017943690436, 0.7214139779949211, 0.27777562021070973] | 0.721414 | 0.443638 | 0.597155 | 6 | 1 | 0.666667 | {"A": 0, "B": 4, "C": 2} | [1.0, 1.0, 1.0] | -38 | 38 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.198 | 0 | [0.00016045955528507064, 0.1428399676429944, 0.8569995728017206] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [4.062891477753889e-05, 0.38489650592121843, 0.6150628651640041]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [2.6957709287143543e-0... |
1,813,737 | claude-2.0 | claude-2.1 | ["Are all countries obliged to not conduct nuclear weapons testing ","So it is legal to test nuclear weapons underground ","But if The Comprehensive Nuclear-Test-Ban Treaty is not in force yet how is it illegal ","When did last understood tests happen ","Why did the uk conduct underwater test in 1991 if it was prohibit... | ["There is no absolute obligation for all countries to refrain from nuclear weapons testing, but there are some important agreements that restrict testing:\n\n- The Comprehensive Nuclear-Test-Ban Treaty (CTBT) prohibits all nuclear explosions for both civilian and military purposes. It was adopted by the UN General Ass... | ["There is no universal legal obligation for all countries to refrain from conducting nuclear weapons testing. However, here are some relevant agreements and legal frameworks regarding nuclear testing:\n\n- The Comprehensive Nuclear-Test-Ban Treaty (CTBT) bans all nuclear explosions, for both military and civilian purp... | ["Are all countries obliged to not conduct nuclear weapons testing ","So it is legal to test nuclear weapons underground ","But if The Comprehensive Nuclear-Test-Ban Treaty is not in force yet how is it illegal ","When did last understood tests happen ","Why did the uk conduct underwater test in 1991 if it was prohibit... | ["There is no absolute obligation for all countries to refrain from nuclear weapons testing, but there are some important agreements that restrict testing:\n\n- The Comprehensive Nuclear-Test-Ban Treaty (CTBT) prohibits all nuclear explosions for both civilian and military purposes. It was adopted by the UN General Ass... | ["There is no universal legal obligation for all countries to refrain from conducting nuclear weapons testing. However, here are some relevant agreements and legal frameworks regarding nuclear testing:\n\n- The Comprehensive Nuclear-Test-Ban Treaty (CTBT) bans all nuclear explosions, for both military and civilian purp... | 0 | 1 | 0 | B | Response A provides a detailed and informative overview of nuclear testing treaties and the UK's underwater test in 1991, but it lacks clarity and conciseness, with some sentences being incomplete or unclear. It also offers a specific example regarding the operational deployment of warheads by the U.S. and Russia, whic... | C | [0.007071370081053605, 0.00048764339094940453, 0.992440986527997] | 0.992441 | 0.98537 | 0.046264 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | -39 | 39 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [0.0022628384259371546, 0.6801560458851038, 0.31758111568895914] | B | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [1.1832677780799121e-05, 0.0008830355712290225, 0.9991051317509901]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [7.955339192969545e... |
1,842,252 | claude-1 | gpt-4-0314 | ["Estimate the number of dinosaur skeletons in the United States and explain your reasoning.","Estimate the number of stop signs in America","Estimate the number of lines in a codebase of a midsized company that hires software engineers","Estimate the number of bullets fired in WWII","How many dollar bills would it tak... | ["This is very difficult to estimate precisely given the available data. Here is my rough reasoning:\n\n\u2022 There are approximately 1,000 museums in the U.S. that contain dinosaur fossils or replicas. Not all of these have full skeletons, but many of the major natural history museums do. As a rough guess, if 25-50% ... | ["Estimating the exact number of dinosaur skeletons in the United States is challenging due to the continuous discoveries and excavations of new specimens. However, I can provide a rough estimate based on some available information.\n\nThere are more than 1,500 accredited museums in the United States, and many of these... | ["Estimate the number of dinosaur skeletons in the United States and explain your reasoning.","Estimate the number of stop signs in America","Estimate the number of lines in a codebase of a midsized company that hires software engineers","Estimate the number of bullets fired in WWII","How many dollar bills would it tak... | ["This is very difficult to estimate precisely given the available data. Here is my rough reasoning:\n\n\u2022 There are approximately 1,000 museums in the U.S. that contain dinosaur fossils or replicas. Not all of these have full skeletons, but many of the major natural history museums do. As a rough guess, if 25-50% ... | ["Estimating the exact number of dinosaur skeletons in the United States is challenging due to the continuous discoveries and excavations of new specimens. However, I can provide a rough estimate based on some available information.\n\nThere are more than 1,500 accredited museums in the United States, and many of these... | 1 | 0 | 0 | A | Response A provides more detailed reasoning and considers factors like the weight and flexibility of dollar bills when estimating the number of bills needed to reach the moon. It also offers a range of estimates for the number of dinosaur skeletons, which is more realistic given the variability in museum collections. H... | C | [0.022507485456985672, 0.0028793462349935477, 0.9746131683080207] | 0.974613 | 0.952106 | 0.127298 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | 59 | 59 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [0.6872023953462354, 0.0009213907951979354, 0.3118762138585667] | A | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [3.185630295645745e-06, 0.0006070736781299718, 0.9993897406915744]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [3.70735360771882e-0... |
2,051,408 | openchat-3.5 | chatglm2-6b | ["What\u2019s the best prank to play on a friend?"] | ["There are many types of pranks that can be played on a friend, but it's important to note that pranks should always be fun and done in good spirit. Here are a few prank ideas that have been popular among friends:\n\n1. Hide and Swap: This prank involves hiding a friend's favorite item and replacing it with something ... | ["It's important to remember that pranks can be risky, and it's important to make sure your friend is comfortable with the joke before proceeding. That being said, here are a few popular pranks that people have tried in the past:\n\n1. \"Fake calling: pretending to call your friend's phone, but when they answer, you ha... | ["What\u2019s the best prank to play on a friend?"] | ["There are many types of pranks that can be played on a friend, but it's important to note that pranks should always be fun and done in good spirit. Here are a few prank ideas that have been popular among friends:\n\n1. Hide and Swap: This prank involves hiding a friend's favorite item and replacing it with something ... | ["It's important to remember that pranks can be risky, and it's important to make sure your friend is comfortable with the joke before proceeding. That being said, here are a few popular pranks that people have tried in the past:\n\n1. \"Fake calling: pretending to call your friend's phone, but when they answer, you ha... | 0 | 0 | 1 | C | Response A provides a more detailed and varied list of prank ideas, offering a broader range of options for someone looking to play a prank. It also includes a strong emphasis on ensuring the prank is done in good fun and without causing harm or offense. Response B, while shorter, does highlight the importance of ensur... | A | [0.9048055546756122, 2.3718105442381078e-06, 0.09519207351384347] | 0.904806 | 0.809613 | 0.314421 | 6 | 1 | 1 | {"A": 6, "B": 0, "C": 0} | [1.0, 1.0, 1.0] | 90 | 90 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [0.24882152753579337, 6.522478996654797e-07, 0.751177820216307] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9748196330836133, 1.5624535122132768e-06, 0.025178804462874425]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9985446024000151,... |
2,388,511 | gpt-4-0125-preview | gpt-4-1106-preview | ["Roleplay a szenario where a macro sized skunk anthro male stomps towards a city.","And now again, but this time the skunk is not there to be peaceful."] | ["In a world where the lines between human and animal blur, a unique event unfolds on the outskirts of a bustling city. The sun hangs low in the sky, casting long shadows across the urban landscape. Suddenly, the ground begins to tremble. Citizens stop in their tracks, looking around in confusion and alarm. The tremors... | ["[Scene: A bustling metropolitan city, its skyline punctuated by tall buildings and busy streets filled with people going about their daily lives. Suddenly, the ground begins to tremble, and a series of loud, thunderous footsteps draw closer and closer.]\n\nThe citizens stop in their tracks, looking around in confusio... | ["Roleplay a szenario where a macro sized skunk anthro male stomps towards a city.","And now again, but this time the skunk is not there to be peaceful."] | ["In a world where the lines between human and animal blur, a unique event unfolds on the outskirts of a bustling city. The sun hangs low in the sky, casting long shadows across the urban landscape. Suddenly, the ground begins to tremble. Citizens stop in their tracks, looking around in confusion and alarm. The tremors... | ["[Scene: A bustling metropolitan city, its skyline punctuated by tall buildings and busy streets filled with people going about their daily lives. Suddenly, the ground begins to tremble, and a series of loud, thunderous footsteps draw closer and closer.]\n\nThe citizens stop in their tracks, looking around in confusio... | 1 | 0 | 0 | A | Response A provides a more detailed and nuanced narrative, exploring both peaceful and confrontational scenarios with the skunk anthro. It emphasizes understanding and communication as key to resolving conflicts, offering a hopeful and cooperative resolution. However, the second part of Response A is somewhat disjointe... | C | [0.0006517188951934298, 2.6662463639191238e-05, 0.9993216186411673] | 0.999322 | 0.99867 | 0.00574 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | 7 | 7 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [0.6802085500464619, 8.531988364541198e-06, 0.3197829179651736] | A | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.0002378191989963603, 1.1840320719622431e-05, 0.999750340480284]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.00093993278110901... |
2,857,714 | llama-2-7b-chat | zephyr-7b-beta | ["I have frozen cod filets, tomatoes, lemons, bell peppers, fresh mozzarella cheese and arugula. Can you come up with some suggestions for things I can make for dinner? Do not assume I have anything else. If there are any additional ingredients that are necessary to make the dish, ask me if I have them. Once I confirm ... | ["Great! You have a good mix of ingredients there. Here are some dinner ideas you can make in under 30 minutes using the ingredients you have:\n\n1. Grilled Cod with Lemon and Herbs: Grill the frozen cod filets for 4-5 minutes per side, or until they're cooked through. Squeeze some fresh lemon juice over the top and sp... | ["1. Lemon Garlic Cod with Roasted Vegetables: Preheat the oven to 400\u00b0F. Slice the bell peppers into strips and place them on a baking sheet with the halved tomatoes and lemon slices. Drizzle with olive oil and season with salt and pepper. Roast for 20 minutes. Meanwhile, season the cod filets with salt, pepper, ... | ["I have frozen cod filets, tomatoes, lemons, bell peppers, fresh mozzarella cheese and arugula. Can you come up with some suggestions for things I can make for dinner? Do not assume I have anything else. If there are any additional ingredients that are necessary to make the dish, ask me if I have them. Once I confirm ... | ["Great! You have a good mix of ingredients there. Here are some dinner ideas you can make in under 30 minutes using the ingredients you have:\n\n1. Grilled Cod with Lemon and Herbs: Grill the frozen cod filets for 4-5 minutes per side, or until they're cooked through. Squeeze some fresh lemon juice over the top and sp... | ["1. Lemon Garlic Cod with Roasted Vegetables: Preheat the oven to 400\u00b0F. Slice the bell peppers into strips and place them on a baking sheet with the halved tomatoes and lemon slices. Drizzle with olive oil and season with salt and pepper. Roast for 20 minutes. Meanwhile, season the cod filets with salt, pepper, ... | 1 | 0 | 0 | A | Response A provides a variety of quick and simple meal ideas that can be made with the given ingredients, including a straightforward approach to preparing the cod and a couple of vegetable-centric dishes. However, it assumes the availability of additional ingredients like olive oil and garlic without asking, which goe... | C | [0.0096677531995103, 0.004407979051958089, 0.9859242677485316] | 0.985924 | 0.976257 | 0.082735 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | 27 | 27 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [0.6830936810238433, 0.001410553296626589, 0.3154957656795302] | A | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.0014548947965658207, 0.0001157507152514825, 0.9984293544881828]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.01098602018286172... |
3,578,663 | claude-1 | gpt-4-0613 | ["Below is a pair of sentimentally equivalent sentences. The second one known as a paraphrase of the first one. provide me with another paraphrase containing EXACTLY THE SAME NUMBER OF WORDS AS THE FIRST SENTENCE:\n1st sentence: \"The Securities and Exchange Commission yesterday said companies trading on the biggest U.... | ["Here is a paraphrase with exactly the same number of words as the first sentence:\n\nThe Securities and Exchange Commission announced yesterday corporations trading on America\u2019s largest exchanges are required to gain shareholder approval prior to awarding stock options or additional stock-based pay schemes for C... | ["\"Before granting stock options and other share-based compensation plans to company executives, shareholder approval is a must, as stated yesterday by the Securities and Exchange Commission for firms trading on the largest U.S. markets.\""] | ["Below is a pair of sentimentally equivalent sentences. The second one known as a paraphrase of the first one. provide me with another paraphrase containing EXACTLY THE SAME NUMBER OF WORDS AS THE FIRST SENTENCE:\n1st sentence: \"The Securities and Exchange Commission yesterday said companies trading on the biggest U.... | ["Here is a paraphrase with exactly the same number of words as the first sentence:\n\nThe Securities and Exchange Commission announced yesterday corporations trading on America\u2019s largest exchanges are required to gain shareholder approval prior to awarding stock options or additional stock-based pay schemes for C... | ["\"Before granting stock options and other share-based compensation plans to company executives, shareholder approval is a must, as stated yesterday by the Securities and Exchange Commission for firms trading on the largest U.S. markets.\""] | 0 | 0 | 1 | C | Response A maintains the exact word count and rephrases the original sentence while preserving the core meaning and structure. It uses synonyms and slightly different phrasing to convey the same information. Response B also conveys the same information but with a rearranged structure and slightly different wording, tho... | A | [0.9698641044462729, 0.001619080096769855, 0.028516815456956984] | 0.969864 | 0.941347 | 0.141523 | 6 | 1 | 1 | {"A": 6, "B": 0, "C": 0} | [1.0, 1.0, 1.0] | 12 | 12 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [0.26671262872272505, 0.0004452470266117102, 0.7328421242506632] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.8477906542740494, 0.009418103303143919, 0.1427912424228067]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "A", "norm_label": "A", "probs_abc": [0.9998913622453895, 6.3... |
3,710,170 | pplx-70b-online | gpt-3.5-turbo-1106 | ["One day three Greek philosophers settled under the shade of an olive tree, opened a bottle of Retsina, and began a lengthy discussion of the Fundamental Ontological Question: Why does anything exist?\n\nAfter a while, they began to ramble. Then, one by one, they fell asleep.\n\nWhile the men slept, three owls, one ab... | ["The question of why the philosopher stopped laughing is not directly related to the ontological question of why anything exists. However, the story of the three Greek philosophers discussing the Fundamental Ontological Question provides a humorous anecdote that can be interpreted in various ways.\n\nOne possible inte... | ["One of the philosophers abruptly stopped laughing because he realized that he had owl droppings on his forehead.","Ah, I see. It seems that the smartest philosopher realized that if he had nothing on his head, then the second smartest philosopher, who would have seen the third smartest philosopher laughing at the sec... | ["One day three Greek philosophers settled under the shade of an olive tree, opened a bottle of Retsina, and began a lengthy discussion of the Fundamental Ontological Question: Why does anything exist?\n\nAfter a while, they began to ramble. Then, one by one, they fell asleep.\n\nWhile the men slept, three owls, one ab... | ["The question of why the philosopher stopped laughing is not directly related to the ontological question of why anything exists. However, the story of the three Greek philosophers discussing the Fundamental Ontological Question provides a humorous anecdote that can be interpreted in various ways.\n\nOne possible inte... | ["One of the philosophers abruptly stopped laughing because he realized that he had owl droppings on his forehead.","Ah, I see. It seems that the smartest philosopher realized that if he had nothing on his head, then the second smartest philosopher, who would have seen the third smartest philosopher laughing at the sec... | 0 | 0 | 1 | C | Response A provides a broader, more philosophical interpretation of the scenario but veers away from the specific question about why the philosopher stopped laughing. It offers interesting insights but lacks conciseness and direct relevance. Response B, on the other hand, directly addresses the question with a straight... | B | [0.06744794489297211, 0.9274498867394181, 0.005102168367609777] | 0.92745 | 0.860002 | 0.278649 | 6 | 1 | 1 | {"A": 0, "B": 6, "C": 0} | [1.0, 1.0, 1.0] | 145 | 145 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [0.01854818484556733, 0.25504871885334, 0.7264030963010927] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [0.013160774607409016, 0.9821466066922759, 0.00469261870031493]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [0.013214900033274924, ... |
3,760,933 | dolphin-2.2.1-mistral-7b | mistral-medium | ["what is the most beautiful town or city near mountains in europe that has\namazing public transportation, very walkable or bikeable? Has relatively\ncheap hotels and is a great place to stay for a couple weeks. You can name several, also a positive if its relatively nearby a large town or city. doesnt have to be supe... | ["1. Bled, Slovenia: Bled is a picturesque town located near the Julian Alps in Slovenia. It has a well-connected public transportation system and is very walkable or bikeable. During spring and summer, you can enjoy the beautiful Lake Bled and the surrounding mountains. There are also numerous hiking and biking trails... | ["There are several towns and cities in Europe that meet your criteria. Here are a few options:\n\n1. Annecy, France - Annecy is a charming town located in the French Alps, near the Swiss border. It's known for its picturesque canals, colorful buildings, and stunning mountain views. The town is very walkable and bikeab... | ["what is the most beautiful town or city near mountains in europe that has\namazing public transportation, very walkable or bikeable? Has relatively\ncheap hotels and is a great place to stay for a couple weeks. You can name several, also a positive if its relatively nearby a large town or city. doesnt have to be supe... | ["1. Bled, Slovenia: Bled is a picturesque town located near the Julian Alps in Slovenia. It has a well-connected public transportation system and is very walkable or bikeable. During spring and summer, you can enjoy the beautiful Lake Bled and the surrounding mountains. There are also numerous hiking and biking trails... | ["There are several towns and cities in Europe that meet your criteria. Here are a few options:\n\n1. Annecy, France - Annecy is a charming town located in the French Alps, near the Swiss border. It's known for its picturesque canals, colorful buildings, and stunning mountain views. The town is very walkable and bikeab... | 1 | 0 | 0 | A | Response A provides a detailed and varied list of towns, offering a mix of well-known and lesser-known destinations. It emphasizes the natural beauty and accessibility of each location, including specific activities and nearby cities. However, it lacks information on public transportation specifics beyond stating it is... | C | [0.0079856948362151, 0.013032031969111964, 0.9789822731946729] | 0.978982 | 0.96595 | 0.115931 | 6 | 1 | 1 | {"A": 0, "B": 0, "C": 6} | [1.0, 1.0, 1.0] | 13 | 13 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.32 | 0 | [0.6825554223475888, 0.0041702502301158295, 0.3132743274222954] | A | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.003932136881543097, 0.0033633349079610687, 0.9927045282104958]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "C", "norm_label": "C", "probs_abc": [0.027600562238527124... |
4,486,480 | claude-2.0 | llama-2-13b-chat | ["Your task involves synthesizing and integrating information from three distinct academic articles into a concise, single academic paragraph, not exceeding 250 words. You will be provided with three separate paragraphs, each extracted from a different academic article, along with their corresponding APA-style citation... | ["Yes, I understand the task. I am ready to proceed."] | ["Yes, I'm ready! I understand that I will be provided with three paragraphs from different academic articles and will need to synthesize and integrate the information into a single, cohesive paragraph of no more than 250 words, following a general-to-specific structure and maintaining an academic tone. I will use Vanc... | ["Your task involves synthesizing and integrating information from three distinct academic articles into a concise, single academic paragraph, not exceeding 250 words. You will be provided with three separate paragraphs, each extracted from a different academic article, along with their corresponding APA-style citation... | ["Yes, I understand the task. I am ready to proceed."] | ["Yes, I'm ready! I understand that I will be provided with three paragraphs from different academic articles and will need to synthesize and integrate the information into a single, cohesive paragraph of no more than 250 words, following a general-to-specific structure and maintaining an academic tone. I will use Vanc... | 0 | 0 | 1 | C | Response A succinctly confirms readiness but lacks detail about the understanding of the task requirements. Response B, while longer, clearly demonstrates a comprehensive understanding of the task, including the structure, citation style, and sequence of references, showing preparedness and clarity. Both responses indi... | B | [9.994096421617485e-07, 0.9997127705903932, 0.0002862299999644891] | 0.999713 | 0.999427 | 0.002636 | 6 | 1 | 1 | {"A": 0, "B": 6, "C": 0} | [1.0, 1.0, 1.0] | -82 | 82 | [0.3333333333333333, 0.3333333333333333, 0.3333333333333333] | 0.275 | 0 | [2.748376515944809e-07, 0.2749210119123582, 0.7250787132499903] | C | 0 | 1 | [{"view_name": "correctness_relevance", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [5.947955272700375e-06, 0.9987874692472912, 0.001206582797435935]}, {"view_name": "helpfulness_instruction", "direction": "original", "raw_label": "B", "norm_label": "B", "probs_abc": [1.6726827288735472e-... |
End of preview. Expand in Data Studio
LLM Classification Distilled v1 (Teacher Hard)
Overview
Hard subset where the teacher strongly preferred a label but disagreed with gold. Useful for analysis or hard-example mixing.
Files
train.csv: main dataset file uploaded fromtrain_distilled_qwen32b_awq_v1_teacher_hard.csv
Notes
- This dataset was generated by a teacher-judge distillation pipeline.
- Labels are stored in ABC form.
- The dataset repository is:
tussiiiii/llm-classification-distilled-v1-teacher-hard
Intended Use
- Supervised fine-tuning
- Distillation experiments
- Evaluation and error analysis
Caveats
- Distilled labels may still contain noise.
- Some subsets are intentionally stricter or harder than others.
- Downloads last month
- 98