LennartKeller/mPhonBench

36 downloads in 30 days1 likesLast modified 2 Nov 2026View on Hugging Face

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 ffb2451
Licence files: No licence file at the top level of the repositoryEvidence: file list at ffb2451
Declared sources: None listed in the card metadata
Access gated on Hugging Face: Yes

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

Tasks

Citation text from the card

@inproceedings{keller-glavas-2026-mphonbench,
    title = "m{P}hon{B}ench: Evaluating {LLM}s On Multilingual Phonology",
    author = "Keller, Lennart  and
      Glava{\v{s}}, Goran",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2456/",
    doi = "10.18653/2026.emnlp-main.2456",
    pages = "55752--55783",
    ISBN = "979-8-89176-459-0",
    abstract = "Phonological competence - knowledge of how surface characters encode underlying pronunciation - underpins applications from poetry generation to speech recognition. Although text-only Large Language Models (LLMs) receive no direct phonetic supervision, prior work shows that they nonetheless develop such competence in English. It remains, however, unclear (1) whether this generalizes across languages and scripts and (2) how this text-based phonological knowledge interacts with the audio processing competencies of speech-augmented LLMs (SLLMs). In this work, we introduce mPhonBench, a massively multilingual benchmark that probes text-only and speech-augmented LLMs for phonological knowledge, spanning 10 tasks, 58 diverse languages, and 19 scripts. While mPhonBench is text-centric, we compl

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": "LennartKeller/mPhonBench" })
signal: "permissive"
stated_licence: "cc-by-sa-4.0"
sources: 0