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

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

Question

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

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": "Finally, User: Thank you, that's all I need. Good bye.\nBefore that, Assistant: Booking was successful.\nReference number is : EPWUAWM5.\nBefore that, User: Okay, book it for 4 nights starting Saturday.\nBefore that, Assistant: Booking was unsuccessful.\nBefore that, User: Could you book it for 3 people and 4 nights starting from thursday?\nBefore that, Assistant: You are looking for the bridge guest house\nBefore that, User: I'm looking for a place. I think it's called like Bridge House or Bridge Guesthouse or something.",
  "question": "What emotion does the final user message express, taking the conversation into account?",
  "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 0 — Neutral Different 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

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/951d42c35c1050050170/presentation_order/reverse_presentation/clean-source_first_emowoz_original_final_reverse_full_0425

Input fingerprint: 0dea98908d2edc942fc46d4d9642c4d59b5e9c96162e3e19e7d3bc7bfd89ef04

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.