Speaking of Language: Reflections on Metalanguage Research in NLP
Not on the map. Why?
Abstract (arXiv)
This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs' metalanguage-centered efforts. Finally, we discuss four dimensions of metalanguage and metalinguistic tasks, offering a list of understudied future research directions.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 83 references that are in the map. First posted on arXiv 3 Apr 2026.
Builds on
31 of 83 references.
References · 31
- 2022Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 smallcited by 1,165
- 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
- 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 564
- 2019Linguistic Knowledge and Transferability of Contextual Representationscited by 383
- 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 75
- 2025Language Models Fail to Introspect About Their Knowledge of Languagecited by 30
- 2024LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languagescited by 28
- 2024Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?cited by 23
- 2024NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helpscited by 20
- 2023Large Linguistic Models: Investigating LLMs' metalinguistic abilitiescited by 18
- 2024Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problemcited by 17
- 2024Linguini: A benchmark for language-agnostic linguistic reasoningcited by 17
19 more
- 2021Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLPcited by 16
- 2020PuzzLing Machines: A Challenge on Learning From Small Datacited by 15
- 2023"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representationcited by 15
- 2020SIGTYP 2020 Shared Task: Prediction of Typological Featurescited by 13
- 2025Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchucited by 13
- 2024Back to School: Translation Using Grammar Bookscited by 11
- 2021Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modelingcited by 10
- 2023Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representationcited by 10
- 2024I am a Strange Dataset: Metalinguistic Tests for Language Modelscited by 10
- 2020Automatic Extraction of Rules Governing Morphological Agreementcited by 9
- 2024Natural Language Processing RELIES on Linguisticscited by 9
- 2022ELQA: A Corpus of Metalinguistic Questions and Answers about Englishcited by 8
- 2023The Past, Present, and Future of Typological Databases in NLPcited by 7
- 2025Explicit Learning and the LLM in Machine Translationcited by 6
- 2025LingGym: How Far Are LLMs from Thinking Like Field Linguists?cited by 6
- 2021When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selectioncited by 5
- 2025Prompting from the bench: Large-scale pretraining is not sufficient to prepare LLMs for ordinary meaning analysiscited by 4
- 2022Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learningcited by 3
- 2023CuRIAM: Corpus re Interpretation and Metalanguage in U.S. Supreme Court Opinionscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
- 2026LLM Agents as Computational Typologistscited by 0
- 2026LLM Agents as Computational Typologists7 Sep 2026