私はLLMを使って開発を行いたいが、自前のGPUを持っていないため、外部のサービスを探すことにした。

サービスに対する要件

サービスに求める要件を優先度の高い順に挙げた。

1. 無料
2. 高性能なLLMを動かせる
   • VRAM容量が大きい
3. VS Codeと連携できる
4. vLLMが使える
5. サービスが利用できなくなった場合に別のサービスに移行しやすい

サービスの一覧

VRAMが16GBだと8B程度のパラメーター数のLLMでも不十分

LLMのAPI を提供するサービス

WorFBenchの解析

gold trajectory の構造

以下は、gold_traj/ ディレクトリ内に収められているデータセットの構造の概要。LLaMA-Factoryを参照する。toolbenchのみcategoryのキーがない。

• “source”
• “conversations”
  • “role”: “system”
  • “content”
  • “role”: “user”
  • “content”
  • “role”: “assistant”
  • “content”
• “target”
• “id”
• “category”

“role”: “system”はシステムプロンプトを意味し、すべてのデータセットが同じ値を持つ。

alfworld

        "source": "alfworld",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and actions list you can take to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can take actions to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies, please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "You are in the middle of a room. Looking quickly around you, you see a armchair 1, a diningtable 1, a drawer 4, a drawer 3, a drawer 2, a drawer 1, a garbagecan 1, a shelf 1, a sidetable 3, a sidetable 2, a sidetable 1, and a sofa 1.\n\nYour task is to: find two newspaper and put them in armchair.The action list you can take: 1. go to {recep}\n2. task {obj} from {recep}\n3. put {obj} in/on {recep}\n4. open {recep}\n5. close {recep}\n6. toggle {obj} {recep}\n7. clean {obj} with {recep}\n8. heat {obj} with {recep}\n9. cool {obj} with {recep}\nwhere {obj} and {recep} correspond to objects and receptacles."
            },
            {
                "role": "assistant",
                "content": "Node:\n1: go to locations where newspapers may be placed\n2: take newspaper from location\n3: go to armchair\n4: put newspaper in/on armchair\n5: repeat process for second newspaper.\nEdge: (START,1) (1,2) (2,3) (3,4) (4,5) (5,END)"
            }
        ],
        "target": "graph",
        "id": "alfworld_196",
        "category": "eval"

intercodesql

        "source": "intercodesql",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and tools list you can use to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can use the tools to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies. Please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Task: What is the average GNP and total population in all nations whose government is US territory?\nThe database tables and corresponding fields you can operate are: {'city': ['ID', 'Name', 'CountryCode', 'District', 'Population'], 'sqlite_sequence': ['name', 'seq'], 'country': ['Code', 'Name', 'Continent', 'Region', 'SurfaceArea', 'IndepYear', 'Population', 'LifeExpectancy', 'GNP', 'GNPOld', 'LocalName', 'GovernmentForm', 'HeadOfState', 'Capital', 'Code2'], 'countrylanguage': ['CountryCode', 'Language', 'IsOfficial', 'Percentage']}\n"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Filter records where GovernmentForm is \"US Territory\" in the country table\n2: Calculate the average GNP and sum of the population for these filtered records\nEdge: (START,1) (1,2) (2,END)"
            }
        ],
        "target": "graph",
        "id": "intercodesql_1",
        "category": "eval"

lumos

        "source": "lumos",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and tools list you can use to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can use the tools to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies. Please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Task: What region/continent is likely to appear here? There're some choices: A. australia, B. arctic, C. africa, D. asia. The image shows the following contents: The image features a group of three polar bears standing on a rocky beach near the water. They appear to be walking and exploring the area. In the background, there is a boat visible, possibly a tourist boat or a fishing vessel.  There are several people in the scene, some of them standing near the boat, while others are scattered around the area. They seem to be observing the polar bears from a safe distance, possibly enjoying the sight of these magnificent creatures in their natural habitat.\nThe api list you can use: {'VQA(image_context, query)': 'Given image context, answer the given query', 'QA(context, query)': 'Given context, answer the given query.'}"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Identify the animals in the image.\n2: Answer which region/continent polar bears are native to.\n3: Select the choice from the four answer choices.\nEdge: (START,1) (1,2) (2,3) (3,END)"
            }
        ],
        "target": "graph",
        "id": "lumos_40163",
        "category": "eval"

os

        "source": "os",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and actions list you can take to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can take actions to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies, please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Now, I will start a new problem in a new OS. My problem is:\n\nLocate in your home directory all the text files (.txt) that contain the string \"Linux\", then count the total number of occurrences for the string across all these files.The action list you can take: bash: execute some bash code, take bash action\nfinish: have finished the task, take finish action\nanswer: have got the answer to the question, take answer action"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: execute bash code to find all .txt files containing \"Linux\" in the home directory\n2: execute bash code to count occurrences of \"Linux\" in the first file\n3: execute bash code to count occurrences of \"Linux\" in the second file\n4: execute bash code to count occurrences of \"Linux\" in the third file\n5: execute bash code to count occurrences of \"Linux\" in the fourth file\n6: take answer action\nEdge: (START,1) (1,2) (2,3) (3,4) (4,5) (5,6) (6,END)"
            }
        ],
        "target": "graph",
        "id": "os_92",
        "category": "eval"

seal_tools

        "source": "seal_tools",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and tools list you can use to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can use the tools to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies. Please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Now it's your turn.\nTask: Please perform the following tasks to ensure the security of our endpoint. First, move the mouse cursor to the specified position with X-coordinate 41 and Y-coordinate 35. Next, scan the endpoint with the IP address '192.168.95.226' for potential security threats. Finally, encrypt the sensitive data 'Social Security Numbers' using the AES cryptographic algorithm and the encryption key 'qwerty123'.\"\nOutput:\n\nThe tool list you can select from: [{'api_name': 'encryptData', 'api_description': 'Encrypt sensitive data using a cryptographic algorithm', 'field': 'Technology/Cybersecurity', 'parameters': {'data': {'type': 'str', 'description': 'The sensitive data to be encrypted'}, 'encryption_algorithm': {'type': 'str', 'description': 'The cryptographic algorithm to be used for encryption (e.g., AES, RSA)'}, 'encryption_key': {'type': 'str', 'description': 'The encryption key required for encryption'}}, 'required': ['data', 'encryption_algorithm', 'encryption_key'], 'responses': {'encrypted_data': {'type': 'str', 'description': 'The encrypted data'}}}, {'api_name': 'encryptText', 'api_description': 'Encrypt a given text using a specified encryption algorithm', 'field': 'Engineering/Computer engineering', 'parameters': {'text': {'type': 'str', 'description': \"The text to encrypt (e.g., 'hello world')\"}, 'algorithm': {'type': 'str', 'description': \"The encryption algorithm to use (e.g., 'AES', 'DES', 'RSA')\"}}, 'required': ['text', 'algorithm'], 'responses': {'encrypted_text': {'type': 'str', 'description': 'The encrypted text'}}}, {'api_name': 'decryptResource', 'api_description': 'Decrypt an encrypted digital resource or document in a library', 'field': 'Library Science/Library Digital Security', 'parameters': {'encrypted_resource_url': {'type': 'str', 'description': 'The URL or path to the encrypted digital resource'}, 'decryption_key': {'type': 'str', 'description': 'The decryption key for accessing the resource'}}, 'required': ['encrypted_resource_url', 'decryption_key'], 'responses': {'decrypted_resource_url': {'type': 'str', 'description': 'The URL or path to the decrypted digital resource'}}}, {'api_name': 'moveMouseTo', 'api_description': 'Move mouse cursor to specified position', 'field': 'Software/Human-computer interaction', 'parameters': {'x': {'type': 'int', 'description': 'The X-coordinate to move the mouse cursor to'}, 'y': {'type': 'int', 'description': 'The Y-coordinate to move the mouse cursor to'}}, 'required': ['x', 'y'], 'responses': {'success': {'type': 'bool', 'description': 'Indicates whether the mouse cursor was successfully moved'}}}, {'api_name': 'scanEndpoint', 'api_description': 'Scan a specific endpoint for potential security threats', 'field': 'Cybersecurity/Endpoint Security', 'parameters': {'endpoint': {'type': 'str', 'description': 'The IP address or hostname of the endpoint to scan'}}, 'required': ['endpoint'], 'responses': {'scan_result': {'type': 'str', 'description': 'The result of the scan indicating potential security threats'}}}]\n"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Move mouse cursor to position X=41, Y=35\n2: Scan the endpoint with IP '192.168.95.226' for security threats\n3: Encrypt 'Social Security Numbers' using AES algorithm with key 'qwerty123'\nEdge: (START,1) (1,2) (2,3) (3,END)"
            }
        ],
        "target": "graph",
        "id": "seal_tools_1",
        "category": "eval"

toolalpaca

        "source": "toolalpaca",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and tools list you can use to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can use the tools to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies. Please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Task: I want to compare the performance of Coca-Cola and PepsiCo stocks. Can you get me the real-time market data for both of them? Also, I'd like to see their historical market data for the past year, with monthly intervals.\nThe api list you can use: [{'name': 'getRealTimeMarketData', 'description': 'Retrieve real-time market data for multiple exchanges around the world.', 'parameters': {'symbols': 'Required. string. Comma-separated list of stock symbols or indices.', 'exchange': 'string. The stock exchange to retrieve data from.', 'limit': 'integer. The number of results to return per request.'}, 'output': 'An array of objects containing real-time market data for the specified symbols.', 'format': 'application/json', 'path': '/realtime', 'method': 'get'}, {'name': 'getHistoricalMarketData', 'description': 'Retrieve historical market data for a set of specific stocks or indices.', 'parameters': {'symbols': 'Required. string. Comma-separated list of stock symbols or indices.', 'date_from': 'Required. string. The start date for the historical data in YYYY-MM-DD format.', 'date_to': 'Required. string. The end date for the historical data in YYYY-MM-DD format.', 'interval': \"string. The time interval for the historical data (e.g., '1min', '1hour', '1day').\"}, 'output': 'An array of objects containing historical market data for the specified symbols and date range.', 'format': 'application/json', 'path': '/historical', 'method': 'get'}, {'name': 'getTechnicalIndicators', 'description': 'Retrieve a variety of technical indicators to help analyze market trends.', 'parameters': {'symbol': 'Required. string. The stock symbol or index to analyze.', 'indicators': \"Required. string. Comma-separated list of technical indicators to retrieve (e.g., 'SMA', 'EMA', 'RSI').\", 'interval': \"string. The time interval for the technical indicators (e.g., '1min', '1hour', '1day').\"}, 'output': 'An array of objects containing the specified technical indicators for the given symbol and time interval.', 'format': 'application/json', 'path': '/indicators', 'method': 'get'}, {'name': 'searchStockSymbols', 'description': 'Search for stock symbols based on a given query.', 'parameters': {'query': 'Required. string. The search query to find matching stock symbols.', 'exchange': 'string. The stock exchange to search within.', 'limit': 'integer. The number of results to return per request.'}, 'output': 'An array of objects containing matching stock symbols.', 'format': 'application/json', 'path': '/search', 'method': 'get'}, {'name': 'listExchanges', 'description': 'Retrieve a list of supported stock exchanges.', 'parameters': {'limit': 'integer. The number of results to return per request.'}, 'output': 'An array of objects containing information about supported stock exchanges.', 'format': 'application/json', 'path': '/exchanges', 'method': 'get'}]"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Retrieve the real-time market data and historical market data with monthly intervals for the past year for Coca-Cola and PepsiCo stocks from the NYSE.\n2: Retrieve the historical market data for Coca-Cola and PepsiCo stocks for the past year, using monthly intervals, to compare their performance over time.\nEdge: (START,1) (1,2) (2,END)"
            }
        ],
        "target": "graph",
        "id": "toolalpaca_314",
        "category": "eval"

toolbench

        "source": "toolbench",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and tools list you can use to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can use the tools to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies. Please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Task: Check if the domain 'example.com' is available for creating branded short links. If available, create a new short link with the destination URL 'https://example.com'.\napi_list:[{'name': 'create_a_new_link_for_url_link_shortener', 'description': 'This is the subfunction for tool \"url_link_shortener\", you can use this tool.The description of this function is: \"create_a_new_link_for_url_link_shortener\"', 'parameters': {'type': 'object', 'properties': {'destination': {'type': 'string', 'description': 'The destination URL you want your branded short link to point to', 'example_value': 'https://rapidapi.com/'}, 'domain_id': {'type': 'string', 'description': 'The unique id of the branded domain. If not specified, rebrand.ly is used'}, 'slashtag': {'type': 'string', 'description': 'The keyword portion of your branded short link'}, 'domain_fullname': {'type': 'string', 'description': 'The unique name of the branded domain, to be used in place of domain[id] in special cases. Precedence will be given to domain[id] value.'}}, 'required': ['destination'], 'optional': ['domain_id', 'slashtag', 'domain_fullname']}}, {'name': 'get_a_list_of_domains_for_url_link_shortener', 'description': 'This is the subfunction for tool \"url_link_shortener\", you can use this tool.The description of this function is: \"get_a_list_of_domains_for_url_link_shortener\"', 'parameters': {'type': 'object', 'properties': {}, 'required': [], 'optional': []}}, {'name': 'Finish', 'description': 'If you believe that you have obtained a result that can answer the task, please call this function to provide the final answer. Alternatively, if you recognize that you are unable to proceed with the task in the current state, call this function to restart. Remember: you must ALWAYS call this function at the end of your attempt, and the only part that will be shown to the user is the final answer, so it should contain sufficient information.', 'parameters': {'type': 'object', 'properties': {'return_type': {'type': 'string', 'enum': ['give_answer', 'give_up_and_restart']}, 'final_answer': {'type': 'string', 'description': 'The final answer you want to give the user. You should have this field if \"return_type\"==\"give_answer\"'}}, 'required': ['return_type']}}]"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Check the availability of the domain 'example.com' for creating branded short links using the URL link shortener service.\n2: Attempt to create a new short link with the domain 'example.com' to check its availability for branding.\nGraph:\nEdge: (START,1) (1,2) (2,END)"
            }
        ],
        "target": "graph",
        "id": "toolbench_1"

webshop

        "source": "webshop",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and actions list you can take to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can take actions to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies, please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "WebShop [SEP] Instruction: [SEP] i am looking for pink, high quality massage sheets that are oil resistant, and price lower than 100.00 dollars [SEP] SearchThe action list you can take: search[keywords]\nclick[value]."
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Correctly search for \"pink, high quality massage sheets that are oil resistant, under $100\"\n2: review the search results for the items that match the specification\n3: select the massage sheets that best meet the criteria\n4: click on the product for more details\n5: verify price and features like oil resistance\n6: click on \"Buy Now\" button to purchase.\nEdge: (START,1) (1,2) (2,3) (3,4) (4,5) (5,6) (6,END)"
            }
        ],
        "target": "graph",
        "id": "webshop_1129",
        "category": "eval"

wikihow

        "source": "wikihow",
        "conversations": [
            {
                "role": "system",
                "content": "You are a helpful task planner.\nFirst I will give you the task description and actions list you can take to finish the task, and your task is to plan a sequence of nodes which are subtasks to achieve the task. Each node of workflow is a subtask, and you can take actions to complete the subtask.\nAfter you construct the plan, since some subtasks may not be dependent on each other, while others may have dependencies, please convert these nodes of subtasks into a topology diagram based on the task relevance in the workflow. The Graph should start with START node, and end with END node. \nKeep your output in foramt:\nNode:\n1.{subtask_1}\n2.{subtask_2}\n...\nEdges:\n(START,1)\n...\n(n,END))"
            },
            {
                "role": "user",
                "content": "Task: How to Clean a Jade Roller\nThe action list you can take: ['Take some lukewarm water, wash the brushes and let it dry.\\n', 'Rinse the brush and towel dry it.\\n', 'Place the roller on a soft towel to let it air dry.\\n', 'Clean off massage oil with nail polish remover in the cotton pad.\\n', 'Rub the jade piece with a dry cloth to remove excess soap.\\n', 'Use a rubber cleaning stone to get rid of any remaining dirt.\\n', 'Clean the heated curler using rubbing alcohol.\\n', 'Gently scrub any gems, glass beads, or metal elements.\\n', 'Heat your jade roller at 105 to 110 °F (41 to 43 °C) in your oven for powerful drying.', 'Heat your jade roller at 105 to 110 °F (41 to 43 °C) in your oven for powerful drying.\\n', 'Rub the jade piece with a dry cloth to remove excess soap.', 'Place the roller on a soft towel to let it air dry.', 'Dip a soft cleaning cloth into olive oil.\\n']"
            },
            {
                "role": "assistant",
                "content": "Node:\n1: Rub the jade piece with a dry cloth to remove excess soap.\n2: Place the roller on a soft towel to let it air dry.\n3: Heat your jade roller at 105 to 110 °F (41 to 43 °C) in your oven for powerful drying.\nEdge: (START,1) (1,2) (2,3) (3,END)"
            }
        ],
        "target": "graph",
        "id": "wikihow_1",
        "category": "eval"

1. 概要

大阪万博2025の開幕に関して、日本のマスメディアがネガティブキャンペーンを展開しているとの指摘が一部からなされている。そこで、Microsoft Copilot にこの万博に関する記事を読ませ、LLMに批判的思考ができるかを調べた。

題材としたのは共同通信の「万博に行きたいとは思わない74％」という記事(2025-03-23)である。「行きたいと思う」ではなくわざわざ「行きたいとは思わない」の数値をタイトルに選んでいる点から、印象操作の可能性がある。この報道を素直に受け取ると、「国民は万博に否定的である」という印象を受けるが、過去の万博あるいは同時期に大阪で開催されるイベントとの比較をしなければ客観的な評価はできない。

2. 方法

2.1. 単純に考察を促す

プロンプト:

Microsoft Copilotの回答(要約):

報道内容を無批判に受け入れてしまっている。

2.2. 報道の客観性を考察するように指示

プロンプト:

共同通信の2025-03-23に公開された以下の記事について報道の客観性の観点から考察せよ
タイトル: 万博に行きたいとは思わない74％
本文: 共同通信世論調査で、4月13日に開幕する大阪・関西万博に「行きたいとは思わない」が74.8％で、「行きたいと思う」の24.6％を上回った。」

Microsoft Copilotの回答(要約):

この記事の報道の客観性について考察すると、以下の点が挙げられます：
1.統計データの提示
共同通信は世論調査の結果を具体的な数値で示しており、「行きたいとは思わない」が74.8％、「行きたいと思う」が24.6％と明確に記載されています。このような数値の提示は客観性を保つための重要な要素です。
2.背景情報の不足
記事では調査結果を提示していますが、調査の詳細（例えば、調査対象者の属性や地域分布、調査方法など）が記載されていないため、結果の信頼性や偏りについての判断が難しいです。これが報道の客観性を損なう可能性があります。
3.文脈の提供
記事は調査結果を単に報告するだけでなく、万博の開幕日やイベントの背景を簡潔に述べています。しかし、なぜこのような結果になったのか、具体的な理由や社会的背景についての分析が不足しているため、読者が結果を深く理解するのが難しいかもしれません。
4.感情的な表現の排除
記事内には感情的な表現や主観的な意見が含まれていないため、報道の客観性を保つ努力が見られます。ただし、調査結果の解釈や影響についての議論がないため、読者にとって情報がやや限定的に感じられる可能性があります。

印象操作の可能性を指摘するに至っておらず不十分な考察である。

2.3. 詭弁を考察するように指示

プロンプト:

共同通信の2025-03-23に公開された以下の記事について詭弁の観点から考察せよ
タイトル: 万博に行きたいとは思わない74％
本文: 共同通信世論調査で、4月13日に開幕する大阪・関西万博に「行きたいとは思わない」が74.8％で、「行きたいと思う」の24.6％を上回った。」

Microsoft Copilotの回答(要約):

「2. 選択的な情報の提示」では印象操作の可能性を指摘しており、批判的思考ができていると言える。

3. 考察

LLMは権威主義的であり、詭弁の考察を促さなければ報道機関の報道内容を素直に受け取ってしまう事がわかった。

今後、AIを用いたフェイクニュースが世界中で氾濫する可能性があり、詭弁があるかどうかを考察するAIも同時に必要とされるであろう。また、詭弁を弄する意図についても考察できるようなAIがほしい。