Papers › Mission: Impossible Language Models

Mission: Impossible Language Models

12 Jan 2024arXiv:2401.06416archive 2025-07-28

Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, Christopher Potts

Chomsky and others have very directly claimed that large language models (LLMs) are equally capable of learning languages that are possible and impossible for humans to learn. However, there is very little published experimental evidence to support such a claim. Here, we develop a set of synthetic impossible languages of differing complexity, each designed by systematically altering English data with unnatural word orders and grammar rules. These languages lie on an impossibility continuum: at one end are languages that are inherently impossible, such as random and irreversible shuffles of English words, and on the other, languages that may not be intuitively impossible but are often considered so in linguistics, particularly those with rules based on counting word positions. We report on a wide range of evaluations to assess the capacity of GPT-2 small models to learn these uncontroversially impossible languages, and crucially, we perform these assessments at various stages throughout training to compare the learning process for each language. Our core finding is that GPT-2 struggles to learn impossible languages when compared to English as a control, challenging the core claim. More importantly, we hope our approach opens up a productive line of inquiry in which different LLM architectures are tested on a variety of impossible languages in an effort to learn more about how LLMs can be used as tools for these cognitive and typological investigations.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 10 ran (7 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jkallini/mission-impossible-language-models officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (3 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
5ran
2unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jkallini/mission-impossible-language-models. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

jkallini/mission-impossible-language-models official repository 12 samples, 10 ran (3 instrument-failed) · 2 unverified
compute_surprisals utils.py ran MIT (permissive) · a1988a1ab7fefaaf · report fixture: signature model:callable/0/?, input_ids:Tensor/2/int · returned list · level recorded 2026-09-24
compute_token_probabilities utils.py ran MIT (permissive) · 5bf34dc8d206d531 · report fixture: signature model:callable/0/?, input_ids:Tensor/2/int, token_id:int/0/int, pad_token_id:int/0/int · returned list · level recorded 2026-09-24
create_attention_mask in 5 papers perplexities/perplexities.py ran · honoured contract MIT (permissive) · ff77cf33dcba8fb3 · report fixture: signature token_lists:list/1/list · returned Tensor · level recorded 2026-09-24
create_input_ids perplexities/perplexities.py ran · honoured contract MIT (permissive) · 547978906e547397 · report fixture: signature token_lists:list/1/list, pad_token_id:int/0/int · returned Tensor · level recorded 2026-09-24
extract_phrases edge_probing/load_phrase_data.py ran MIT (permissive) · f954e3cc5ab8a96a · report fixture: signature tree:Tree/1/Tree, categories:list/1/str · returned list · level recorded 2026-09-24
get_perplexities perplexities/perplexities.py ran MIT (permissive) · 50924a7f63ced3d3 · report fixture: signature model:callable/0/?, token_lists:list/1/list, pad_token_id:int/0/int, device:str/0/str · returned list · level recorded 2026-09-24
get_span in 8 papers edge_probing/load_phrase_data.py ran MIT (permissive) · 74f6c2941d16cfcf · report fixture: signature tokens:list/1/int, sub_tokens:list/1/int · returned tuple · level recorded 2026-09-24
max_pooling in 11 papers edge_probing/edge_probing.py ran; the contract check could not run (RAISES) MIT (permissive) · bdb37b344c1fbfc5 · report fixture: signature tensor:Tensor/3/float, index_tuples:list/1/tuple · returned Tensor · level recorded 2026-09-24
mean_pooling in 71 papers edge_probing/edge_probing.py ran; the contract check could not run (RAISES) MIT (permissive) · 7b8787922f993a93 · report fixture: signature tensor:Tensor/3/float, index_tuples:list/1/tuple · returned Tensor · level recorded 2026-09-24
process_file in 33 papers edge_probing/load_phrase_data.py ran · our draft was wrong MIT (permissive) · 2dfc460bf3c3be3c · report fixture: signature file:str/0/str · returned list · level recorded 2026-09-24
get_gpt2_tokenizer_with_markers utils.py unverified MIT (permissive) · 6b2f4c65ccfed139 · report
get_layer_embedding edge_probing/edge_probing.py unverified MIT (permissive) · 63f2e3ec2da6c808 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSETSoftmaxWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections