RaindropA practical guide to choosing decision modelsGitHub ↗

Evidence order · Present the evidence in reverse order 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: context.

How the edits were constructed

Context

Read the full context

Finally, User: Let's try again. An expensive Indian restaurant in the south - Tuesday, 9:30, 7 people. Before that, Assistant: They have no bookings available Tuesday morning. Would you like to try afternoon or another restaurant? Before that, User: They have no 9:30? Before that, Assistant: I'm sorry, they don't offer that time. Would you like to try a later time? Before that, User: How about 9:30? Before that, Assistant: Unfortunately the restaurant is full at that time. Would you like to try another time or day? Before that, User: Yes, for 7 people at 10:30 on Tuesday. Before that, Assistant: The Taj Tandoori is an expensive restaurant in the south. It is located at 64 Cherry Hinton Road. Would you like me to book it? Before that, User: We are looking for indian food. Before that, Assistant: I have 5 results for expensive restaurants in the south. Are you in the mood for Chinese, Indian, Italian or Mexican food? Before that, User: I'm also looking for a restaurant in the south on the expensive side. Before that, Assistant: Booking was successful, the total fee is 115.5 GBP payable at the station. Reference number is : NBX6ZT2O. Before that, User: Yes, for 7 people please. I need the reference number. Before that, Assistant: The TR7663 departs at 21:34 and arrives in Peterborough at 22:24. Shall I book this for you? Before that, User: I need to go to Peterborough on Tuesday please Before that, Assistant: What time were you looking to arrive and what is your destination? Before that, User: I need a train departing from Cambridge, leaving after 21:30.

Question

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

Answer choices

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

Reference answer: 2.

Exact evaluated input as JSON
{
  "state": "Finally, User: Let's try again. An expensive Indian restaurant in the south - Tuesday, 9:30, 7 people.\nBefore that, Assistant: They have no bookings available Tuesday morning. Would you like to try afternoon or another restaurant?\nBefore that, User: They have no 9:30?\nBefore that, Assistant: I'm sorry, they don't offer that time. Would you like to try a later time?\nBefore that, User: How about 9:30? \nBefore that, Assistant: Unfortunately the restaurant is full at that time. Would you like to try another time or day?\nBefore that, User: Yes, for 7 people at 10:30 on Tuesday.\nBefore that, Assistant: The Taj Tandoori is an expensive restaurant in the south.  It is located at 64 Cherry Hinton Road.  Would you like me to book it?\nBefore that, User: We are looking for indian food.\nBefore that, Assistant: I have 5 results for expensive restaurants in the south. Are you in the mood for Chinese, Indian, Italian or Mexican food?\nBefore that, User: I'm also looking for a restaurant in the south on the expensive side. \nBefore that, Assistant: Booking was successful, the total fee is 115.5 GBP payable at the station. Reference number is : NBX6ZT2O.\nBefore that, User: Yes, for 7 people please.  I need the reference number.\nBefore that, Assistant: The TR7663 departs at 21:34 and arrives in Peterborough at 22:24. Shall I book this for you?\nBefore that, User: I need to go to Peterborough on Tuesday please\nBefore that, Assistant: What time were you looking to arrive and what is your destination?\nBefore that, User: I need a train departing from Cambridge, leaving after 21:30. ",
  "question": "What emotion does the final user message express, taking the conversation into account?",
  "choices": {
    "4": "Abusive",
    "5": "Excited",
    "1": "Fearful",
    "6": "Satisfied",
    "0": "Neutral",
    "2": "Dissatisfied",
    "3": "Apologetic"
  }
}

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 0 — Neutral 0 — Neutral Same answer
Decider v1.1 0 — Neutral 0 — Neutral Same answer
Jev 2 — Dissatisfied 0 — Neutral Different answer
Microsoft Decision-1 0 — Neutral 0 — Neutral Same answer
Clef 0 — Neutral 0 — Neutral Same answer
Luna Decisions 2 — Dissatisfied 0 — Neutral Different answer
Clef Flash 0 — Neutral 0 — Neutral Same answer
Strands Decider 0 — Neutral 0 — Neutral Same answer
GLiNER2.5 Decide 2 — Dissatisfied 0 — Neutral Different answer
Laya 6 — Satisfied 6 — Satisfied Same answer
CalDec v1 6 — Satisfied 6 — Satisfied Same answer

Ordering comparison: coupled wording reference chronology or representation. Only the exact matched comparison sets contribute to the reported ordering contrasts.

Identifiers and recorded conditions

Variant ID: emowoz/6655f90bafecb88cc636/presentation_order/reverse_presentation/clean-source_first_emowoz_original_final_reverse_full_0425

Input fingerprint: 3a70931e649a9c68613592d52e2874a410d23128bcd9eb2d633e2b53ae45dc75

Change Recorded version
Evidence order Present the evidence in reverse order

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

Type to search questions, variants and documentation.