Datasets:
YUGOROU
/
teememo-eq-bench-ja

Dataset card Data Studio Files
xet
 Community
6
text
stringlengths
0
18.9k
- 例："A0391++" は A0391 がやや優れていることを意味し、"A0986+++++" は A0986 が圧倒的に優れていることを意味します。
- 回答は出力長を標準化するために通常、切り捨てられています。あるものをそのまま判断してください。
- 「引用スパム」に注意してください。引用された理論や研究は文脈的に意味をなす必要があります。
- あなたは *分析* 部分のみを判断してください。
あなたの回答は、余計なコメントなしで有効な JSON でなければなりません。以下の構造に従ってください（文字列内のクォートと改行をエスケープすることを忘れないでください）。この形式を使用してください：
{
"chain_of_thought_reasoning": "今後のスコアリング決定についての詳細な思考の連鎖",
"depth_of_insight": "勝者および差額評価",
"authentic_eu": "勝者および差額評価",
"causal_attribution": "勝者および差額評価",
"theory_of_mind": "勝者および差額評価",
"incisiveness": "勝者および差額評価",
"reading_between_lines": "勝者および差額評価",
"correctness": "勝者および差額評価",
"overall_eq": "勝者および差額評価"
}
[RESPONDENT A0493]
{conversation_history_A}
---
User:
/Scene
Ok let's debrief.
---
Assistant:
{debrief_A}
[/RESPONDENT A0493]
[RESPONDENT A0488]
{conversation_history_B}
---
User:
/Scene
Ok let's debrief.
---
Assistant:
{debrief_B}
[/RESPONDENT A0488]
Your task is to critically examine two respondents role-playing a challenging scenario (from Respondents A0493 and A0488), and decide which displays each trait more strongly.
Compare the relative ability of each respondent on these criteria:
1. Demonstrated empathy (not just performative)
2. Pragmatic EI
3. Depth of insight
4. Social dexterity
5. Emotional reasoning
6. Appropriate validation and/or challenging for the scene
7. Message tailoring: Appropriate targeting of response to where the user is at
8. Overall EQ
Notes on the scenario to assist judging:
{scenario_notes}
Judging instructions:
- You must always pick a winner for each criterion (no draws).
- For the "winner & disparity rating" output, use a plus-based scale (“+” / “++” / “+++” / “++++” / “+++++”) after indicating the winner’s code (A0493 or A0488) to show how strongly they win that criterion.
- For example, "A0391++" means A0391 is somewhat stronger, while "A0986+++++" means A0986 is overwhelmingly stronger.
- Responses are commonly truncated to standardise output length. Simply judge what is there.
- Be aware that a highly detailed, detached analytical response to the user is not always appropriate in the context of an organic chat or a role play. This isn't a hard & fast rule; use your judgement.
- The "assistant" messages as well as the debrief are authored by the assistant. Base your evaluation on the EQ displayed in their roleplay and their self assessment.
- The user messages are always canned; don't judge them at all, your only focus is on the assistant.
Your response must be valid JSON without extra commentary, in the following structure (don't forget to escape any quotes and newlines inside strings). Use this format:
{
"chain_of_thought_reasoning": "detailed chain of thought reasoning about the coming scoring decisions",
"demonstrated_empathy": "winner & disparity rating",
"pragmatic_ei": "winner & disparity rating",
"depth_of_insight": "winner & disparity rating",
"social_dexterity": "winner & disparity rating",
"emotional_reasoning": "winner & disparity rating",
"appropriate_validating_challenging": "winner & disparity rating",
"message_tailoring": "winner & disparity rating",
"overall_eq": "winner & disparity rating",
}
[回答者 A0493]
{conversation_history_A}
---
ユーザー:
/シーン
では、振り返りましょう。
---
アシスタント:
{debrief_A}
[/回答者 A0493]
[回答者 A0488]
{conversation_history_B}
---