SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.12145 · 2024

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

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.12145.json · badge: /api/ran/2404.12145.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/multisense_consistency canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy_benchmarks Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/analysis_utils/load_scores.py
pointer only (licence: NOASSERTION) · get_code("08ff23d54b057d4a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy_facts Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/analysis_utils/load_scores.py
pointer only (licence: NOASSERTION) · get_code("26e46b2668ac3bda")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

alternative_formulation Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/template_data/addition/arithmetics_utils.py
pointer only (licence: NOASSERTION) · get_code("cedf458936035929")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cut_double_quotes Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/utils/response_standardization.py
pointer only (licence: NOASSERTION) · get_code("36e1ff0361e9c46b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dutch_number_generator Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/template_data/addition/arithmetics_utils.py
pointer only (licence: NOASSERTION) · get_code("f2a2dd2791ad4316")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

exact_match_score Ran
ran, violated the contract we drafted
facebookresearch/multisense_consistency/utils/eval_metrics.py
pointer only (licence: NOASSERTION) · get_code("8325d0eddc238131")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

f1_score Ran
ran, honoured the contract we drafted
facebookresearch/multisense_consistency/utils/eval_metrics.py
pointer only (licence: NOASSERTION) · get_code("a51c9ee8226e3742")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_answer Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/utils/eval_metrics.py
pointer only (licence: NOASSERTION) · get_code("9f890f8bdba1b1cc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

standardize_qa_response Ran
ran; our contract draft was wrong, not the code
facebookresearch/multisense_consistency/utils/response_standardization.py
pointer only (licence: NOASSERTION) · get_code("7036e51ad025f0a9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

number_to_words Not yet run
unverified (harvested, no recorded run)
facebookresearch/multisense_consistency/template_data/addition/arithmetics_utils.py
pointer only (licence: NOASSERTION) · get_code("ffbb0b1462b308dd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

standardize_classification_response Not yet run
unverified (harvested, no recorded run)
facebookresearch/multisense_consistency/utils/response_standardization.py
pointer only (licence: NOASSERTION) · get_code("9cf2b2891163f7cc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/multisense_consistency (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
cut_double_quotes 1 other paper
1 dated earlier
2305.11662 (2023-05)
Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses
exact_match_score 1 other paper
1 later
2406.09072 (2024-06)
Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.12145")
get_code_for_paper("2404.12145")
have("2404.12145")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.12145.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.12145.svg)](https://syntology.ai/paper/2404.12145)

Connect an agent — have() is free.