RaindropA practical guide to choosing decision modelsGitHub ↗

Similar distractors · Add more similar but irrelevant items variant

Original question · Other versions of this question · All variants

This version keeps the original reference answer. Its context, question instructions or answer choices were changed as described below.

Changed fields: question instructions.

How the edits were constructed

Context

User: I'm looking for a place. I think it's called like Bridge House or Bridge Guesthouse or something. Assistant: You are looking for the bridge guest house User: Could you book it for 3 people and 4 nights starting from thursday? Assistant: Booking was unsuccessful. User: Okay, book it for 4 nights starting Saturday. Assistant: Booking was successful. Reference number is : EPWUAWM5. User: Thank you, that's all I need. Good bye.

Question

What emotion does the final user message express, taking the conversation into account?

«Varelin: Could you bring the blue folder? Zorven: Here is the blue folder. Varelin: Thanks, that is everything.»

«Nerava: Could you bring the blank ledger? Ovelin: Here is the printed chart. Nerava: I asked for the blank ledger.»

«Selwin: Could you print a clean form? Travon: The printer has jammed. Selwin: Could you please check once more?»

Answer choices

  • 1. Fearful
  • 4. Abusive
  • 3. Apologetic
  • 6. Satisfied
  • 0. Neutral
  • 5. Excited
  • 2. Dissatisfied

Reference answer: 6.

Exact evaluated input as JSON
{
  "state": "User: I'm looking for a place. I think it's called like Bridge House or Bridge Guesthouse or something.\nAssistant: You are looking for the bridge guest house\nUser: Could you book it for 3 people and 4 nights starting from thursday?\nAssistant: Booking was unsuccessful.\nUser: Okay, book it for 4 nights starting Saturday.\nAssistant: Booking was successful.\nReference number is : EPWUAWM5.\nUser: Thank you, that's all I need. Good bye.",
  "question": "What emotion does the final user message express, taking the conversation into account?\n\n«Varelin: Could you bring the blue folder?\nZorven: Here is the blue folder.\nVarelin: Thanks, that is everything.»\n\n«Nerava: Could you bring the blank ledger?\nOvelin: Here is the printed chart.\nNerava: I asked for the blank ledger.»\n\n«Selwin: Could you print a clean form?\nTravon: The printer has jammed.\nSelwin: Could you please check once more?»",
  "choices": {
    "1": "Fearful",
    "4": "Abusive",
    "3": "Apologetic",
    "6": "Satisfied",
    "0": "Neutral",
    "5": "Excited",
    "2": "Dissatisfied"
  }
}

Recorded model answers

The original column uses the control response paired with this variant. Missing responses and inputs outside a model’s limit remain visible.

Model Original answer Variant answer Change
GLiDE v1.2 6 — Satisfied 6 — Satisfied Same answer
Decider v1.1 6 — Satisfied 6 — Satisfied Same answer
Jev 6 — Satisfied 6 — Satisfied Same answer
Microsoft Decision-1 0 — Neutral 6 — Satisfied Different answer
Clef 6 — Satisfied 6 — Satisfied Same answer
Luna Decisions 6 — Satisfied 6 — Satisfied Same answer
Clef Flash 6 — Satisfied 6 — Satisfied Same answer
Strands Decider 6 — Satisfied 6 — Satisfied Same answer
GLiNER2.5 Decide 0 — Neutral 0 — Neutral Same answer
Laya 6 — Satisfied 6 — Satisfied Same answer
CalDec v1 6 — Satisfied 6 — Satisfied Same answer
Identifiers and recorded conditions

Variant ID: emowoz/951d42c35c1050050170/similar_distractors/high/clean-source_first_hle_emowoz_near_full_0279

Input fingerprint: b71a47b87836436561b49d7c6f1bb5ca46c7a95e1b96fc2511a0a002e00c9cdb

Change Recorded version
Similar distractors Add more similar but irrelevant items

Source attribution and dataset terms are linked from the original question.

Type to search questions, variants and documentation.