All datasets / NeoHugh

NeoHugh/TrapQA

112 downloads in 30 days1 likesLast modified 27 Oct 2026View on Hugging Face

Permissive or share-alike

The declared licence (cc-by-sa-4.0) is classified as share-alike.

Declared licence: cc-by-sa-4.0, from the tagEvidence: README.md at 628c5f8
Licence files: No licence file at the top level of the repositoryEvidence: file list at 628c5f8
Declared sources: None listed in the card metadata
Access gated on Hugging Face: No

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

question-answering

Citation text from the card

@inproceedings{hu-etal-2026-understanding,
    title = "Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors",
    author = "Hu, Yangfan  and
      Tong, Xuhan  and
      Bai, Haoyue  and
      Ding, Xi  and
      Bharadwaj, Shashank Muralidhar  and
      Cao, Siyang  and
      Nowak, Robert D  and
      Zhang, Jiawei",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.2092/",
    pages = "44555--44581",
    ISBN = "979-8-89176-462-0",
    abstract = "Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or whether the model has the relevant information but follows the wrong inference path. We study this phenomenon as *inference misalignment*: a mismatch between the answer supported by the prompt and the answer favored by statistically salient latent associations. We formalize this view with a latent key{--}task model, in which pretraining-frequency imbalance can cause a shortcut path to dominate the constraint-sensitive path and induce positive inference loss. The framework predicts two failure modes

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "NeoHugh/TrapQA" })
signal: "permissive"
stated_licence: "cc-by-sa-4.0"
sources: 0