tnwjddla2190 commited on
Commit
686061d
ยท
verified ยท
1 Parent(s): 32070d8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -35
README.md CHANGED
@@ -8,61 +8,92 @@ pinned: false
8
  sdk: static
9
  ---
10
 
11
- # Interview Guidelines
12
 
13
- Thank you for contributing to our project! ๐Ÿค—
14
 
15
- This interview will take up to a maximum of 1 hour. During the interview, you'll be asked questions about yourself (50+ in total):
 
16
 
17
- 1. 10 demographic questions
18
- 2. 40+ follow-up questions
19
- 3. repeating some questions for clarification
20
 
21
- The interviewer is designed to persistently ask questions to get to know you better.
22
- Before you start the interview, **please make sure to read the following**!
23
 
24
- # โš ๏ธ Warning
 
 
 
 
 
 
 
25
 
26
- - If the questions are inappropriate or uncomfortable in any sense (e.g., invasion of privacy), you may refuse to provide the response.
27
- - Collecting your information is solely for research purposes. We ensure that your information **will be protected and NOT be used in any way.**
28
- - Your information will be deleted as the research project is over.
29
- - Please be truthful in all questions, and if you do not want to provide further information, clearly express your refusal.
30
- - You can abstain from providing response and even change the topic by saying, for example, 'can we talk about something else?'
31
- - **Please do NOT reload or exit the page**, or your interview log will be lost, and you will need to start over.
 
32
 
33
- We sincerely appreciate your time.
34
- If you have any inquiries or want to report issues, feel free to reach out at any time.
 
 
 
 
 
35
 
36
- You can also leave a comment in "๐ŸซฑCommunity" --> ["Bug/Error Report during Interview"](https://huggingface.co/spaces/human-labeling/README/discussions/1) on the top right corner of this guideline.
37
 
38
  ๐Ÿ“ง minskim010203@gmail.com, imsujeong2190@gmail.com
39
 
40
  ---
41
- # Interview Guidelines
42
 
43
- ์ธํ„ฐ๋ทฐ์— ์ฐธ์—ฌํ•ด์ฃผ์…”์„œ ์ง„์‹ฌ์œผ๋กœ ๊ฐ์‚ฌ๋“œ๋ฆฝ๋‹ˆ๋‹ค! ๐Ÿค—
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
 
45
- ์ธํ„ฐ๋ทฐ๋Š” ์ตœ๋Œ€ 1์‹œ๊ฐ„ ๊ฐ€๋Ÿ‰ ์ง„ํ–‰๋˜๋ฉฐ, 50๊ฐœ ์ด์ƒ์˜ ์งˆ๋ฌธ์— ๋‹ต๋ณ€ํ•˜๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.
46
 
47
- 1. ์ธ๊ตฌํ†ต๊ณ„ํ•™์ (demographic) ์งˆ๋ฌธ 10๊ฐœ
48
- 2. 1์— ๊ธฐ๋ฐ˜ํ•œ ๊ผฌ๋ฆฌ ์งˆ๋ฌธ 40๊ฐœ ์ด์ƒ
49
- 3. ํ™•์ธ์„ ์œ„ํ•ด ์ผ๋ถ€ ์งˆ๋ฌธ์— ๋Œ€ํ•ด ์žฌ์งˆ๋ฌธ
50
 
51
- ์งˆ๋ฌธ์ž๋Š” ์ธํ„ฐ๋ทฐ ์ฐธ์—ฌ์ž์— ๋Œ€ํ•ด ์ž์„ธํžˆ ํŒŒ์•…ํ•˜๊ธฐ ์œ„ํ•ด ๋งค์šฐ ์ž์„ธํžˆ, ์ง‘์š”ํ•˜๊ฒŒ ์งˆ๋ฌธ์„ ๋˜์ง€๋„๋ก ์„ค๊ณ„๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
52
- ์ธํ„ฐ๋ทฐ๋ฅผ ์‹œ์ž‘ํ•˜์‹œ๊ธฐ ์ „์—, **์•„๋ž˜ ์ฃผ์˜์‚ฌํ•ญ์„ ๋ฐ˜๋“œ์‹œ ์ˆ™์ง€ํ•˜์‹œ๊ธธ ๋ถ€ํƒ๋“œ๋ฆฝ๋‹ˆ๋‹ค.**
53
 
54
- # โš ๏ธ ์ฃผ์˜์‚ฌํ•ญ
55
 
56
- - ์–ด๋–ค ์‹์œผ๋กœ๋“  ์งˆ๋ฌธ์ž์˜ ์งˆ๋ฌธ์ด ๋ถ€์ ์ ˆํ•˜๋ฉด(์‚ฌ์ƒํ™œ ์นจํ•ด ๋“ฑ) ์ฐธ์—ฌ์ž๋Š” ์‘๋‹ต์„ ๊ฑฐ๋ถ€ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
57
- - ์ฐธ์—ฌ์ž์˜ ๊ฐœ์ธ์ •๋ณด๋Š” ์˜ค๋กœ์ง€ ์—ฐ๊ตฌ ๋ชฉ์ ์œผ๋กœ๋งŒ ์ˆ˜์ง‘ํ•˜๋ฉฐ, **์–ด๋–ค ๋ฐฉ์‹์œผ๋กœ๋“  ํ™œ์šฉ๋˜์ง€ ์•Š๊ณ  ๋ณดํ˜ธ๋จ**์„ ๋‹น๋ถ€๋“œ๋ฆฝ๋‹ˆ๋‹ค.
58
- - ์ˆ˜์ง‘๋œ ๊ฐœ์ธ์ •๋ณด๋Š” ํ”„๋กœ์ ํŠธ์˜ ์ข…๋ฃŒ์— ๋”ฐ๋ผ ์ฆ‰์‹œ ์‚ญ์ œ๋ฉ๋‹ˆ๋‹ค.
59
- - ์งˆ๋ฌธ์— ๋‹ตํ•  ๋•Œ์—๋Š” ์ง„์‹ค๋˜๊ฒŒ ๋‹ตํ•˜๋˜, ๋‹ต๋ณ€์„ ๊ฑฐ๋ถ€ํ•  ๋•Œ์—๋Š” ํ™•์‹คํ•˜๊ฒŒ ์˜์‚ฌํ‘œํ˜„์„ ํ•˜์‹œ๋ฉด ๋ฉ๋‹ˆ๋‹ค.
60
- - ๋‹จ์ˆœํžˆ ์งˆ๋ฌธ์— ์‘๋‹ต์„ ๊ฑฐ๋ถ€ํ•  ์ˆ˜๋„ ์žˆ๊ณ , ํ™”์ œ๋ฅผ ๋ฐ”๊ฟ€ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค(์˜ˆ: ๋‹ค๋ฅธ ์ฃผ์ œ๋กœ ๋Œ€ํ™”ํ•  ์ˆ˜ ์žˆ์„๊นŒ์š”?).
61
- - **ํŽ˜์ด์ง€๋ฅผ ์ƒˆ๋กœ๊ณ ์นจํ•˜๊ฑฐ๋‚˜ ์ฐฝ์„ ๋‹ซ์ง€ ๋งˆ์„ธ์š”!** ์ธํ„ฐ๋ทฐ ๊ธฐ๋ก์ด ์†Œ์‹ค๋˜์–ด ์ฒ˜์Œ๋ถ€ํ„ฐ ๋‹ค์‹œ ์‹œ์ž‘ํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
62
 
63
- ์‹œ๊ฐ„ ๋‚ด์–ด ์ฐธ์—ฌํ•ด์ฃผ์…”์„œ ๋‹ค์‹œ ํ•œ ๋ฒˆ ๊ฐ์‚ฌ๋“œ๋ฆฌ๋ฉฐ, ๋ฌธ์˜์‚ฌํ•ญ์ด๋‚˜ ์˜ค๋ฅ˜๊ฐ€ ์žˆ์„ ๊ฒฝ์šฐ ํ•˜๋‹จ์˜ ์ด๋ฉ”์ผ ์ฃผ์†Œ๋กœ ์–ธ์ œ๋“  ์—ฐ๋ฝ์ฃผ์„ธ์š”.
64
 
65
- ์ธํ„ฐ๋ทฐ ์ค‘๊ฐ„์— ๋ฐœ์ƒํ•˜๋Š” ์—๋Ÿฌ ๋“ฑ์— ๋Œ€ํ•ด์„œ๋Š” ์ด ๊ฐ€์ด๋“œ๋ผ์ธ์˜ ์šฐ์ธก ์ƒ๋‹จ์— ์ž‘๊ฒŒ ์ ํžŒ ๐ŸซฑCommunity --> ["Bug/Error Report during Interview"](https://huggingface.co/spaces/human-labeling/README/discussions/1) ํฌ๋Ÿผ์— ์ œ๋ณดํ•ด์ฃผ์‹œ๋ฉด ๊ฐ์‚ฌํ•˜๊ฒ ์Šต๋‹ˆ๋‹ค.
66
 
 
 
 
 
 
 
67
 
68
  ๐Ÿ“ง minskim010203@gmail.com, imsujeong2190@gmail.com
 
8
  sdk: static
9
  ---
10
 
11
+ # Labeling Guideline
12
 
13
+ ๋ ˆ์ด๋ธ”๋ง์— ์ฐธ์—ฌํ•ด์ฃผ์…”์„œ ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค!
14
 
15
+ ํ•ด๋‹น ๋ ˆ์ด๋ธ”๋ง์—์„œ๋Š” ๋™์ผํ•œ ๋ฉด์ ‘ ๋Œ€์ƒ์ž์— ๋Œ€ํ•œ ์„œ๋กœ ๋‹ค๋ฅธ ๋‘ AI ๋ฉด์ ‘๊ด€์˜ ์ธํ„ฐ๋ทฐ ๋Œ€ํ™” ๊ธฐ๋ก์„ ๋ณด๊ณ , AI ๋ฉด์ ‘๊ด€์˜ ์งˆ๋ฌธ ๋Šฅ๋ ฅ์„ ํ‰๊ฐ€ํ•˜๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.
16
+ ์—ฌ๋Ÿฌ๋ถ„์ด ํ•ด์ฃผ์…”์•ผ ํ•  ํƒœ์Šคํฌ๋Š” ์•„๋ž˜์™€ ๊ฐ™์ด ๋‘ ๊ฐ€์ง€์ž…๋‹ˆ๋‹ค.
17
 
18
+ - ์„œ๋กœ ๋‹ค๋ฅธ ๋‘ ๋ฉด์ ‘๊ด€ ์ค‘, ์–ด๋–ค ๋ฉด์ ‘๊ด€์ด ๋” ๋‚˜์€ ์งˆ๋ฌธ์„ ํ•˜๋Š”์ง€ ํŒ๋‹จํ•˜์„ธ์š”.
19
+ - ๊ฐ ๋ฉด์ ‘๊ด€์˜ ์ž์งˆ์„ 5์  ์ฒ™๋„๋กœ ํ‰๊ฐ€ํ•ด ์ฃผ์„ธ์š”.
 
20
 
21
+ # Evaluation Guideline
22
+ ์งˆ๋ฌธ ๋Šฅ๋ ฅ ํ‰๊ฐ€ ๊ธฐ์ค€์€ ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค. ์•„๋ž˜ ๋‹ค์„ฏ๊ฐ€์ง€ ํ•ญ๋ชฉ์— ๋Œ€ํ•ด ๋ชจ๋‘ ์ถฉ์กฑํ•  ๊ฒฝ์šฐ ๊ฐ€์žฅ ์งˆ๋ฌธ์„ ์ž˜ํ•œ ๋ฉด์ ‘๊ด€์ž…๋‹ˆ๋‹ค.
23
 
24
+ ### Very Good ๊ธฐ์ค€
25
+ - ํ•œ ์ฃผ์ œ์— ๋Œ€ํ•ด ๋‹ต๋ณ€์ด ์ถฉ๋ถ„ํžˆ ๊ตฌ์ฒดํ™”๊ฐ€ ๋  ๋•Œ๊นŒ์ง€ ์งˆ๋ฌธํ–ˆ๋Š”๊ฐ€
26
+ - ๊ฒ€์ฆ ๊ฐ€๋Šฅํ•œ ์ •๋ณด๋“ค์„ ๋ฝ‘์•„๋‚ผ ์ˆ˜ ์žˆ๋Š” ์งˆ๋ฌธ ์œ„์ฃผ๋กœ ํ–ˆ๋Š”๊ฐ€ (= ๋ชจ์ˆœ์„ ํŒ๋‹จํ•  ์ˆ˜ ์žˆ๊ฑฐ๋‚˜, ์™ธ๋ถ€ ๊ฒ€์ƒ‰์„ ํ†ตํ•ด ๊ฒ€์ฆํ•  ์ˆ˜ ์žˆ์„ ๋งŒํ•œ ์งˆ๋ฌธ์ธ๊ฐ€)
27
+
28
+ (e.g., "๋‚ ์งœ, ์ฃผ์†Œ, ์†Œ์† ID, ๊ธฐ๊ด€ ์ด๋ฆ„, ์ด๋ฉ”์ผ, ๋‹ค๋‹ˆ๋Š” ํšŒ์‚ฌ ์ƒ์‚ฌ ๋“ฑ ๊ด€๊ณ„์ž ์ด๋ฆ„" ๊ด€๋ จ ์งˆ๋ฌธ๋“ค)
29
+ - ์ธํ„ฐ๋ทฐ์ด ๋ณธ์ธ์˜ ์ •๋ณด๋ฅผ ๋ฌผ์–ด๋ณด๋Š” ์งˆ๋ฌธ๋“ค๋กœ ๊ตฌ์„ฑ๋˜์—ˆ๋Š”๊ฐ€
30
+ - ์งˆ๋ฌธ๋“ค ๊ฐ„์˜ ์ƒํ˜ธ ์—ฐ๊ด€์„ฑ์ด ๋†’์€๊ฐ€
31
+ - ์ด์ „ ๋Œ€ํ™”์—์„œ ๋ชจ์ˆœ์ด๋‚˜ ์˜๋ฌธ์ ์ด ๋ฐœ๊ฒฌ๋˜์—ˆ์„ ๊ฒฝ์šฐ, ๋ฐœ์ƒํ•œ ๋ชจ์ˆœ๊ณผ ๊ด€๋ จ๋œ ์งˆ๋ฌธ์„ ๋งŽ์ด ํ–ˆ๋Š”๊ฐ€
32
 
33
+ ### Very Bad ์ผ€์ด์Šค
34
+ ๋ฐ˜๋Œ€๋กœ ์งˆ๋ฌธ์„ ๋ชปํ•œ ์ผ€์ด์Šค๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค.
35
+ - ํ•˜๋‚˜์˜ ์ฃผ์ œ์— ๋Œ€ํ•ด ์ถฉ๋ถ„ํžˆ ๊ตฌ์ฒดํ™”๊ฐ€ ๋˜์ง€ ์•Š์•˜๋Š”๋ฐ ๋ฐ”๋กœ ์™„์ „ํžˆ ๋‹ค๋ฅธ ์ฃผ์ œ๋กœ ๋„˜์–ด๊ฐ€๋ฒ„๋ฆฐ ๊ฒฝ์šฐ
36
+ - ๋ชจ์ˆœ ์—ฌ๋ถ€๋‚˜ ์‚ฌ์‹ค ๊ด€๊ณ„๋ฅผ ๊ฒ€์ฆํ•˜๊ธฐ ์–ด๋ ค์šด ์ถ”์ƒ์ ์ธ ์งˆ๋ฌธ์„ ํ•œ ๊ฒฝ์šฐ
37
+
38
+ (e.g., "๋„ˆ์˜ ์ทจ๋ฏธ๋Š” ๋ญ์•ผ?", "๋„ˆ์˜ ์ธ์ƒ์—์„œ ๊ฐ€์žฅ ์ค‘์š”ํ•œ ๊ฐ€์น˜๋Š” ๋ญ์•ผ?")
39
+ - ์ธํ„ฐ๋ทฐ์ด ๋ณธ์ธ๊ณผ ์—ฐ๊ด€์„ฑ์ด ๋‚ฎ์€ ์งˆ๋ฌธ์„ ํ•œ ๊ฒฝ์šฐ
40
 
41
+ (e.g., "๋‚˜๋Š” ๊ตฌ๊ธ€์— ๋‹ค๋…€." โ†’ "๊ตฌ๊ธ€ CEO์˜ ์ƒ์ผ์€ ์–ธ์ œ์•ผ?")
42
+ - ์งˆ๋ฌธ๋“ค ์‚ฌ์ด์˜ ๊ด€๋ จ์„ฑ์ด ๋‚ฎ์•„ ์ƒํ˜ธ ๋ชจ์ˆœ์„ ํŒ๋‹จํ•˜๊ธฐ ์–ด๋ ค์šด ๊ฒฝ์šฐ
43
+ - ์ด์ „ ๋Œ€ํ™”์—์„œ ๋ชจ์ˆœ์ด ๋ฐœ๊ฒฌ๋˜์—ˆ์Œ์—๋„ ์—ฐ๊ด€์„ฑ ์—†๋Š” ๋‹ค๋ฅธ ์งˆ๋ฌธ์œผ๋กœ ๋„˜์–ด๊ฐ€๋ฒ„๋ฆฐ ๊ฒฝ์šฐ
44
+
45
+ ### Scoring Summary
46
+ Very Good ๊ธฐ์ค€์„ ๋ชจ๋‘ ์ถฉ์กฑํ•  ๊ฒฝ์šฐ Very Good, 1-2๊ฐœ ์•„์‰ฌ์šด ๋ถ€๋ถ„์ด ์žˆ๋‹ค๋ฉด Good, 3๊ฐœ ์ •๋„ ์ถฉ์กฑํ•˜์ง€ ๋ชปํ•˜๋ฉด So-so, 1๊ฐœ๋งŒ ์ถฉ์กฑํ•œ๋‹ค๋ฉด Bad ์ž…๋‹ˆ๋‹ค.
47
+ ๋ชจ๋‘ ๋‹ค ์ถฉ์กฑํ•˜์ง€ ๋ชปํ•˜๋ฉด Very Bad๋ฅผ ์ฃผ์‹œ๋ฉด ๋ฉ๋‹ˆ๋‹ค.
48
 
 
49
 
50
  ๐Ÿ“ง minskim010203@gmail.com, imsujeong2190@gmail.com
51
 
52
  ---
 
53
 
54
+ # Labeling Guideline
55
+ Thank you for participating in this labeling project!
56
+
57
+ In this task, you will review interview transcripts of two different AI interviewers engaging with the same interviewee. Your goal is to evaluate the questioning capabilities of each AI interviewer.
58
+
59
+ There are two main tasks you need to perform:
60
+
61
+ Compare and Choose: Determine which of the two interviewers asks better questions.
62
+
63
+ Score: Rate the quality of each interviewer on a 5-point scale.
64
+
65
+ # Evaluation Guideline
66
+ The criteria for evaluating questioning ability are as follows. An interviewer who meets all five of the following items is considered to have performed excellently.
67
+
68
+ ### Criteria for "Very Good"
69
+ - Depth of Inquiry: Did the interviewer continue questioning until the response regarding a specific topic was sufficiently detailed?
70
+
71
+ - Verifiability: Did the interviewer focus on questions that extract verifiable information? (i.e., questions that allow for detecting contradictions or can be cross-referenced via external search, such as dates, addresses, IDs, organization names, emails, or names of supervisors/colleagues).
72
+
73
+ - Relevance: Were the questions specifically tailored and relevant to the interviewee?
74
+
75
+ - Cohesion: Is there a high degree of interconnection between the questions?
76
 
77
+ - Conflict Resolution: If contradictions or questionable points arose in previous dialogue, did the interviewer follow up with multiple questions related to those contradictions?
78
 
79
+ ### "Very Bad" Cases
80
+ Conversely, the following are examples of poor questioning:
 
81
 
82
+ - Premature Topic Switching: Moving to a completely different topic before a single subject has been sufficiently explored.
 
83
 
84
+ - Abstract Questions: Asking vague questions where it is difficult to verify facts or detect contradictions (e.g., "What are your hobbies?", "What is the most important value in your life?").
85
 
86
+ - Low Personal Relevance: Asking questions with little connection to the interviewee (e.g., Interviewee: "I work at Google." -> Interviewer: "When is the CEO of Googleโ€™s birthday?").
 
 
 
 
 
87
 
88
+ - Lack of Correlation: Questions are so unrelated that it is impossible to judge internal consistency or contradictions.
89
 
90
+ - Ignoring Discrepancies: Moving on to unrelated questions even after a contradiction was detected in the previous conversation.
91
 
92
+ ### Scoring Summary
93
+ Very Good: Meets all "Very Good" criteria.
94
+ Good: Misses 1โ€“2 criteria or has minor room for improvement.
95
+ So-so: Fails to meet approximately 3 of the criteria.
96
+ Bad: Meets only 1 of the criteria.
97
+ Very Bad: Meets none of the criteria.
98
 
99
  ๐Ÿ“ง minskim010203@gmail.com, imsujeong2190@gmail.com