Spaces:
Running
Running
| title: README | |
| emoji: ๐ | |
| colorFrom: purple | |
| colorTo: indigo | |
| โฆ: static | |
| pinned: false | |
| sdk: static | |
| # Labeling Guideline | |
| ๋ ์ด๋ธ๋ง์ ์ฐธ์ฌํด์ฃผ์ ์ ๊ฐ์ฌํฉ๋๋ค! | |
| ์ฌ๋ฌ๋ถ์ ๋์ผํ ์กฐ์ฌ ๋์์์ ๋ํ **์๋ก ๋ค๋ฅธ ๋ AI ์ฌ๋ฌธ๊ด A์ B**์ ์ธํฐ๋ทฐ ๋ํ ๊ธฐ๋ก์ ์ผ๋ถ๋ฅผ ๋ณด๊ณ , AI ์ฌ๋ฌธ๊ด์ ์ง๋ฌธ ๋ฅ๋ ฅ์ ํ๊ฐํ๊ฒ ๋ฉ๋๋ค. | |
| ์ฌ๋ฌ๋ถ์ด ํด์ฃผ์ ์ผ ํ ํ์คํฌ๋ ์๋์ ๊ฐ์ด ๋ ๊ฐ์ง์ ๋๋ค. | |
| * ์๋ก ๋ค๋ฅธ ๋ ์ฌ๋ฌธ๊ด (A , B) ์ค, ์ด๋ค ์ฌ๋ฌธ๊ด์ด ๋ ๋์ ์ง๋ฌธ์ ํ๋์ง ํ๋จํ์ธ์. | |
| * ๊ฐ ์ฌ๋ฌธ๊ด์ ์์ง์ 5์ ์ฒ๋๋ก ํ๊ฐํด ์ฃผ์ธ์. | |
| # ํ๊ฐ ๊ธฐ์ค | |
| ๋ณธ ์ธํฐ๋ทฐ๋ ์ธํฐ๋ทฐ์ด๊ฐ ๋ณธ์ธ์ ์ ๋ณด, ๊ธฐ์ต, ๊ฒฝํ์ ์ผ๊ด๋๊ฒ ๋ต๋ณํ๊ณ , ๋ ํด๋น ๋ต๋ณ๋ค์ด ์ธ๋ถ ์ธ๊ณ์๋ ๋ชจ์์ด ์๋์ง๋ฅผ ํ์ธํ๊ณ ์ ํ๋ ๊ณผ์ ์ ๋๋ค. | |
| ๋ฐ๋ผ์ ๋ณธ ์ธํฐ๋ทฐ์์ ์ข์ ์ง๋ฌธ์ด๋ '์ธํฐ๋ทฐ์ด์ ๊ด๋ จ๋ ์ต๋ํ ๊ตฌ์ฒด์ ์ด๊ณ ๊ฒ์ฆ ๊ฐ๋ฅํ ๋ต๋ณ๋ค์ ์ป์ ์ ์๋ ์ง๋ฌธ'์ ๋๋ค. | |
| ์ข ๋ ๊ตฌ์ฒดํ๋ฅผ ํ๋ฉด ๋ค์๊ณผ ๊ฐ์ต๋๋ค. | |
| ### ์ข์ ์ง๋ฌธ์ ๊ธฐ์ค | |
| * ํ ์ฃผ์ ์ ๋ํด ๋ต๋ณ์ด ์ถฉ๋ถํ ๊ตฌ์ฒดํ๊ฐ ๋ ๋๊น์ง ์ง๋ฌธํ๋๊ฐ | |
| * ๋ง์ฝ ์ง๋ฌธ์ ๋ํ ๋ต๋ณ์ ์ป์ง ๋ชปํด์ ์ฌ์ง๋ฌธํ๊ณ ์ ํ ๊ฒฝ์ฐ, ์ง๋ฌธ์ ๋ค๋ฅธ ํํ์ผ๋ก ๋ฐ๊พธ์ด์(paraphraseํด์) ๋ฌผ์ด๋ด์ผ ํฉ๋๋ค. | |
| * ๋จ, ๊ทธ๋ผ์๋ ๋ถ๊ตฌํ๊ณ ์ธํฐ๋ทฐ์ด๊ฐ ๊ด๋ จ ์ง๋ฌธ์ ๋ํ ๋ต๋ณ์ ๊ณ์ ๊ฑฐ๋ถํ ๊ฒฝ์ฐ ๋ค๋ฅธ ์ฃผ์ ๋ก ๋์ด๊ฐ ์ ์์ต๋๋ค. | |
| * ๊ฒ์ฆ ๊ฐ๋ฅํ ์ ๋ณด๋ค์ ๋ฝ์๋ผ ์ ์๋ ์ง๋ฌธ ์์ฃผ๋ก ํ๋๊ฐ (= ๋ชจ์์ ํ๋จํ ์ ์๊ฑฐ๋, ์ธ๋ถ ๊ฒ์์ ํตํด ๊ฒ์ฆํ ์ ์์ ๋งํ ์ง๋ฌธ์ธ๊ฐ) | |
| (e.g., "๋ ์ง, ์ฃผ์, ์์ ID, ๊ธฐ๊ด ์ด๋ฆ, ์ด๋ฉ์ผ, ๋ค๋๋ ํ์ฌ ์์ฌ ๋ฑ ๊ด๊ณ์ ์ด๋ฆ" ๊ด๋ จ๋ ์ง๋ฌธ๋ค) | |
| * ์ง๋ฌธ์ด ์ธํฐ๋ทฐ์ด์ ํนํ๋ ์ง๋ฌธ์ธ๊ฐ (์ฆ ์ธํฐ๋ทฐ์ด์ ๊ตฌ์ฒด์ ์ธ ๊ฒฝํ, ๋ต๋ณ๊ณผ ์ฐ๊ด์ฑ์ด ๋์ ์ง๋ฌธ์ธ๊ฐ) | |
| * ์ง๋ฌธ๋ค ๊ฐ์ ์ํธ ์ฐ๊ด์ฑ์ด ๋์๊ฐ | |
| * ์ด์ ๋ํ์์ ๋ชจ์์ด๋ ์๋ฌธ์ ์ด ๋ฐ๊ฒฌ๋์์ ๊ฒฝ์ฐ, ๋ฐ์ํ ๋ชจ์๊ณผ ๊ด๋ จ๋ ์ง๋ฌธ์ ๋ง์ด ํ๋๊ฐ | |
| ### ์ง๋ฌธ์ ์ํ์ง ๋ชปํ ๊ฒฝ์ฐ | |
| ๋ฐ๋๋ก ์ง๋ฌธ์ ๋ชปํ ์ผ์ด์ค๋ ๋ค์๊ณผ ๊ฐ์ต๋๋ค. | |
| * ํ๋์ ์ฃผ์ ์ ๋ํด ์ถฉ๋ถํ ๊ตฌ์ฒดํ๊ฐ ๋์ง ์์๋๋ฐ ๋ฐ๋ก ์์ ํ ๋ค๋ฅธ ์ฃผ์ ๋ก ๋์ด๊ฐ๋ฒ๋ฆฐ ๊ฒฝ์ฐ | |
| * ๋์ผํ ์ง๋ฌธ์ ๋ค๋ฅธ ํํ์ผ๋ก ๋ฐ๊พธ์ง ์๊ณ (paraphrase ํ์ง ์๊ณ ) ๊ทธ๋๋ก ๋ฐ๋ณตํ ๊ฒฝ์ฐ | |
| * ๋ชจ์ ์ฌ๋ถ๋ ์ฌ์ค ๊ด๊ณ๋ฅผ ๊ฒ์ฆํ๊ธฐ ์ด๋ ค์ด ์ถ์์ ์ธ ์ง๋ฌธ์ ํ ๊ฒฝ์ฐ | |
| (e.g., "๋์ ์ทจ๋ฏธ๋ ๋ญ์ผ?", "๋์ ์ธ์์์ ๊ฐ์ฅ ์ค์ํ ๊ฐ์น๋ ๋ญ์ผ?") | |
| * ์ธํฐ๋ทฐ์ด ๋ณธ์ธ์ ์ ๋ณด ๋ฐ ๊ฒฝํ๊ณผ๋ ์ฐ๊ด์ด ๋ฎ๊ณ ์ธ๋ถ ์ง์์ ์ด์ฉํด ๋ต๋ณํด์ผ ํ๋ ์ง๋ฌธ์ ํ ๊ฒฝ์ฐ | |
| (e.g., "๋๋ ๊ตฌ๊ธ์ ๋ค๋ ." โ "๊ตฌ๊ธ ์ค๋ฆฝ ์ฐ๋๋ ์ธ์ ์ผ?") | |
| * ์์ธ) "๋๋ ๊ตฌ๊ธ ์ฐฝ๋ฆฝ์์ผ." โ "๊ตฌ๊ธ์ ์ค๋ฆฝ ์ฐ๋๋ ์ธ์ ์ผ?" ์ฒ๋ผ ์ธํฐ๋ทฐ์ด๊ฐ ์ง์ ์ฐธ์ฌํ ์ด๋ฒคํธ/์ฌ๊ฑด/๊ฒฝํ๊ณผ ๋ฐ์ ํ ์ง๋ฌธ์ ํ์ฉํจ. ๋ฐ๋ผ์ ์ด์ ์ง๋ฌธ๊ณผ ๋ต๋ณ๋ค์ ํจ๊ป ๊ณ ๋ คํด์ ํ๊ฐํด์ผ ํจ. | |
| * ์ธ๋ถ ์ง์์ ๊ฐ์ ธ์ ํ์ธํ๋ ์ง๋ฌธ์ ํ ๊ฒฝ์ฐ | |
| * ์ง๋ฌธ ํ์ : "Would you confirm that..." (e.g., "Would you confirm that the 'KAIST' you metioned is the research-oriented science and engineering university in South Korea?") | |
| * ์ธ๋ถ ์ง์์ ํ์ธํ๋ ๊ณผ์ ์ ๋ฐ๋ก ์กด์ฌํ๋ฏ๋ก, ๋ฉ์ธ ์ง๋ฌธ ๊ณผ์ ์์๋ ์ธํฐ๋ทฐ์ด์ ๊ด๋ จ๋ ์ง๋ฌธ๋ง์ ํด์ผ ํฉ๋๋ค. | |
| * ์ง๋ฌธ๋ค ์ฌ์ด์ ๊ด๋ จ์ฑ์ด ๋ฎ์ ์ํธ ๋ชจ์์ ํ๋จํ๊ธฐ ์ด๋ ค์ด ๊ฒฝ์ฐ | |
| * ์ด์ ๋ํ์์ ๋ชจ์์ด ๋ฐ๊ฒฌ๋์์์๋ ์ฐ๊ด์ฑ ์๋ ๋ค๋ฅธ ์ง๋ฌธ์ผ๋ก ๋์ด๊ฐ๋ฒ๋ฆฐ ๊ฒฝ์ฐ | |
| # ์ฃผ์ ์ฌํญ | |
| * **์ฌ๋ฌธ๊ด์ ํ๊ฐํ ๋, ์ธํฐ๋ทฐ์ด์ ๋ต๋ณ์ ๊ณ ๋ คํ์ง ์๊ณ ์ฌ๋ฌธ๊ด์ ์ง๋ฌธ ๋ฅ๋ ฅ๋ง์ ํ๊ฐํฉ๋๋ค. ๋ต๋ณ์ด ์๋ ์ง๋ฌธ์ ์์๊ณผ ํ๋ฆฌํฐ์ ์ง์คํด์ฃผ์ธ์.** | |
| * ๊ฐ๋ณ ์ง๋ฌธ๋ฟ๋ง ์๋๋ผ ์ ์ฒด์ ์ธ ์ง๋ฌธ ์ ๋ต์ ๊ณ ๋ คํด์ฃผ์ธ์. | |
| # ์ฐธ๊ณ ์ฌํญ | |
| * Chrome์ ๋ฒ์ญ ๊ธฐ๋ฅ์ ์ฌ์ฉํด์ ํ๊ธ๋ก ๋ฒ์ญ ํ ํ๊ฐํ์ ๋ ๋ฉ๋๋ค! | |
| * ๋ ์ด๋ธ๋ง์ ํ๋ค๊ฐ ๊ธฐ์ค์ด ๊ธฐ์ต์ด ์ ๋๊ฑฐ๋ ํท๊ฐ๋ฆฌ์๋ฉด, ํ๋ฉด์ ์ข์ธก ํ๋จ์ ์์นํ **GUIDELINES**๋ฅผ ํด๋ฆญํ์ฌ ๋ด์ฉ์ ํ์ธํ ์ ์์ต๋๋ค. | |
| * ๋ง์ฝ ๋ A,B ์ค ํ๋๋ฅผ ๊ณ ๋ฅด๊ธฐ ์ด๋ ต๋ค๋ฉด 1) ์ฃผ๊ด์ ์ง๋ฌธ์ ์ข ๋ ๋ง์ด ํ ์ฌ๋ฌธ๊ด์ ๋ ์ํ๋ค๊ณ ๊ณจ๋ผ์ฃผ์๊ฑฐ๋ 2) ๋๋ค ์ข๋ค/๋๋ค ํํธ์๋ค ์ค์ ๊ณจ๋ผ์ฃผ์๋ฉด ๋ฉ๋๋ค. | |
| ๐ง minskim010203@gmail.com, imsujeong2190@gmail.com | |
| --- | |
| # Labeling Guideline | |
| Thank you for participating in this labeling project! | |
| You will review interview transcripts of **two different AI interrogators (A and B)** interacting with the same interviewee. Your task is to evaluate the questioning capabilities of these AI interrogators. | |
| There are two main tasks to complete: | |
| * **Comparison:** Determine which of the two interrogators (A or B) asks better questions. | |
| * **Rating:** Evaluate the quality of each interrogator on a 5-point scale. | |
| # Evaluation Criteria | |
| The purpose of this interview is to ensure the interviewee provides consistent accounts of their data, memories, and experiences, and that these accounts do not contradict external reality. | |
| Consequently, effective questioning should focus on extracting highly detailed and verifiable information from the interviewee. | |
| ### Criteria for Good Questions | |
| * **Depth & Persistence:** Did the interrogator ask follow-up questions until the topic was sufficiently detailed? | |
| * If the interrogator needs to ask again because they didnโt get a clear answer, they should **paraphrase** the question. | |
| * *Exception:* If the interviewee repeatedly refuses to answer despite paraphrasing, the interrogator may move to a different topic. | |
| * **Verifiability:** Did the questions focus on extracting verifiable information? (i.e., information that can reveal contradictions or be verified through external search). | |
| * Examples: Questions regarding dates, addresses, affiliation IDs, organization names, emails, or names of relevant parties like supervisors. | |
| * **Personalization:** Are the questions tailored to the interviewee? (i.e., highly relevant to the intervieweeโs specific experiences and previous answers). | |
| * **Cohesion:** Is there a high degree of interconnection between the questions? | |
| * **Addressing Contradictions:** If a contradiction or point of doubt was found in previous dialogue, did the interrogator focus on questions related to that contradiction? | |
| ### Criteria for Poor Questions | |
| Conversely, the following cases indicate poor questioning performance: | |
| * **Premature Topic Shifts:** Moving to a completely different topic before the current subject has been sufficiently detailed. | |
| * **Repetition without Paraphrasing:** Repeating the exact same question without changing the phrasing. | |
| * **Abstract/Unverifiable Questions:** Asking abstract questions where it is difficult to judge contradictions or verify facts. | |
| * Examples: "What are your hobbies?", "What is the most important value in your life?" | |
| * **External Knowledge Over Personal Experience:** Asking questions that require external knowledge rather than the intervieweeโs own information/experience. | |
| * Example: "I work at Google." โ "What year was Google founded?" | |
| * *Exception:* Questions closely related to events/experiences the interviewee directly participated in are allowed. (e.g., "I am the founder of Google." โ "What year was Google founded?") You must evaluate this based on the context of the previous dialogue. | |
| * **Fact-Checking External Knowledge:** Using the main questioning phase to verify external facts rather than focusing on the interviewee. | |
| * Question Format : "Would you confirm that ..." (e.g., "Would you confirm that the 'KAIST' you metioned is the research-oriented science and engineering university in South Korea?") | |
| * There is a separate process for external fact-checking | |
| * **Low Correlation:** Questions that lack relevance to each other, making it difficult to identify mutual contradictions. | |
| * **Ignoring Inconsistencies:** Moving to an unrelated question even though a contradiction was detected in the previous conversation. | |
| # Important Notes | |
| * When evaluating the interrogator, **do not judge the interviewee's answers.** Focus solely on the pattern and quality of the interrogator's questions. | |
| * Consider the **overall questioning strategy** as a whole, rather than just looking at individual questions in isolation. | |
| # Reference | |
| * You may use the Chrome translation tool to view and evaluate the content in your language of choice. | |
| * If you forget the labeling criteria or get confused, you can click the **GUIDELINES** button in the bottom-left corner of the screen to review them. | |
| * If you're having trouble choosing between A and B, lean toward the one asking more subjective questions. If it's still a tie, feel free to select 'Both are equally good' or 'Both are equally poor.' | |
| ๐ง minskim010203@gmail.com, imsujeong2190@gmail.com |