Papers › From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using...

From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency

18 Apr 2024arXiv:2404.12145archive 2025-07-28

Xenia Ohmer, Elia Bruni, Dieuwke Hupkes

The staggering pace with which the capabilities of large language models (LLMs) are increasing, as measured by a range of commonly used natural language understanding (NLU) benchmarks, raises many questions regarding what "understanding" means for a language model and how it compares to human understanding. This is especially true since many LLMs are exclusively trained on text, casting doubt on whether their stellar benchmark performances are reflective of a true understanding of the problems represented by these benchmarks, or whether LLMs simply excel at uttering textual forms that correlate with what someone who understands the problem would say. In this philosophically inspired work, we aim to create some separation between form and meaning, with a series of tests that leverage the idea that world understanding should be consistent across presentational modes - inspired by Fregean senses - of the same meaning. Specifically, we focus on consistency across languages as well as paraphrases. Taking GPT-3.5 as our object of study, we evaluate multisense consistency across five different languages and various tasks. We start the evaluation in a controlled setting, asking the model for simple facts, and then proceed with an evaluation on four popular NLU benchmarks. We find that the model's multisense consistency is lacking and run several follow-up analyses to verify that this lack of consistency is due to a sense-dependent task understanding. We conclude that, in this aspect, the understanding of LLMs is still quite far from being consistent and human-like, and deliberate on how this impacts their utility in the context of learning about human language and understanding.

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 9 ran (4 with no instrument failure; 5 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.

facebookresearch/multisense_consistency officialmentioned in paperNOASSERTIONSyntology: 11 samples, 9 ran (5 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 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.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
2ran
2unverified

Licence: 11 of the 11 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 facebookresearch/multisense_consistency. “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.

facebookresearch/multisense_consistency official repository 11 samples, 9 ran (5 instrument-failed) · 2 unverified
accuracy_benchmarks analysis_utils/load_scores.py ran licence not identified · pointer only · 08ff23d54b057d4a · report fixture: signature combine:bool/0/bool, response_mapping:bool/0/bool, ablation:NoneType/0/?, external:bool/0/bool · returned tuple · level recorded 2026-09-24
accuracy_facts analysis_utils/load_scores.py ran · our draft was wrong licence not identified · pointer only · 26e46b2668ac3bda · report fixture: signature languages:tuple/1/str · returned tuple · level recorded 2026-09-24
alternative_formulation template_data/addition/arithmetics_utils.py ran fingerprinted licence not identified · pointer only · cedf458936035929 · report fixture: signature language:str/0/str, number_in_words:str/0/str · returned list · level recorded 2026-09-24
cut_double_quotes utils/response_standardization.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 36e1ff0361e9c46b · report fixture: signature old_datapoint:str/0/str · returned str · level recorded 2026-09-24
dutch_number_generator template_data/addition/arithmetics_utils.py ran · our draft was wrong fingerprinted licence not identified · pointer only · f2a2dd2791ad4316 · report fixture: signature input_number:str/0/str · returned str · level recorded 2026-09-24
exact_match_score in 82 papers utils/eval_metrics.py ran · violated contract fingerprinted licence not identified · pointer only · 8325d0eddc238131 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-24
f1_score in 121 papers utils/eval_metrics.py ran · honoured contract fingerprinted licence not identified · pointer only · a51c9ee8226e3742 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-24
normalize_answer in 304 papers utils/eval_metrics.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 9f890f8bdba1b1cc · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
standardize_qa_response utils/response_standardization.py ran · our draft was wrong licence not identified · pointer only · 7036e51ad025f0a9 · report fixture: signature responses:list/1/str, labels:list/1/list · returned tuple · level recorded 2026-09-24
number_to_words template_data/addition/arithmetics_utils.py unverified licence not identified · pointer only · ffbb0b1462b308dd · report
standardize_classification_response utils/response_standardization.py unverified licence not identified · pointer only · 9cf2b2891163f7cc · report

Tasks

FormLanguage ModellingNatural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutFocusGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight 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