SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.13469 · 2024

Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2406.13469.json · badge: /api/ran/2406.13469.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
ScandEval/ScandEval community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
get_closest_match Ran
ran on a synthesized input
ScandEval/ScandEval/src/euroeval/closest_match.py
code served (permissive licence) · get_code("76fd1517c3722774")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import collections.abc as c

# Set up arguments for get_closest_match function
ARGS = {
    "string": "hello",
    "options": ["hallo", "helo", "world", "help"],
    "case_sensitive": False,
    "insertion_weight": 1,
    "deletion_weight": 1,
    "substitution_weight": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
Levenshtein — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_package_version Ran
ran on a synthesized input
ScandEval/ScandEval/src/euroeval/data_models.py
code served (permissive licence) · get_code("7e78af0cca343023")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import importlib.metadata

# The function takes a package_name (str) and returns its version or None
# It uses importlib.metadata.version() which just needs a valid package name string

# We can test with a commonly available package that should be installed
ARGS = {
    "package_name": "importlib_metadata"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_custom_datasets_module Ran
ran on a synthesized input
ScandEval/ScandEval/src/euroeval/custom_dataset_configs.py
code served (permissive licence) · get_code("c77577a25a058035")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned module. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import logging
from pathlib import Path

# Create a temporary Python file to serve as the custom datasets module
temp_dir = tempfile.TemporaryDirectory()
temp_path = Path(temp_dir.name)

# Create a simple custom datasets file
custom_datasets_file = temp_path / "custom_datasets.py"
custom_datasets_file.write_text("""
# Simple custom datasets module
def get_dataset():
    return "custom_dataset"
""")

# Set up logging to avoid AttributeError on log_once
class MockLogger:
    def __init__(self):
        self.logged = set()
    
    def log_once(self, message, level):
        if message not in self.logged:
            logging.log(level, message)
            self.logged.add(message)

# Monkey-patch log_once if it doesn't exist in the module's namespace
import sys
current_module = sys.modules[__name__]
if not hasattr(current_module, 'log_once'):
    def log_once(message, level):
        logging.log(level, message)

ARGS = {
    "custom_datasets_file": custom_datasets_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_data Not yet run
unverified (harvested, no recorded run)
ScandEval/ScandEval/src/euroeval/data_loading.py
code served (permissive licence) · get_code("4d6e325649536cf4")
How it ran

no invocation recorded.

load_raw_data Not yet run
unverified (harvested, no recorded run)
ScandEval/ScandEval/src/euroeval/data_loading.py
code served (permissive licence) · get_code("009eb05ddfea0cb3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

This paper explores the performance of encoder and decoder language models on multilingual Natural Language Understanding (NLU) tasks, with a broad focus on Germanic languages. Building upon the ScandEval benchmark, initially restricted to evaluating encoder models, we extend the evaluation framework to include decoder models. We introduce a method for evaluating decoder models on NLU tasks and apply it to the languages Danish, Swedish, Norwegian, Icelandic, Faroese, German, Dutch, and English. Through a series of experiments and analyses, we also address research questions regarding the comparative performance of encoder and decoder models, the impact of NLU task types, and the variation across language resources. Our findings reveal that encoder models can achieve significantly better NLU performance than decoder models despite having orders of magnitude fewer parameters. Additionally, we investigate the correlation between decoders and task performance via a UMAP analysis, shedding light on the unique capabilities of decoder and encoder models. This study contributes to a deeper understanding of language model paradigms in NLU tasks and provides valuable insights for model selection and evaluation in multilingual settings.

For agents

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

get_harvested_code_for_paper("2406.13469")
get_code_for_paper("2406.13469")
have("2406.13469")

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

curl https://syntology.ai/api/ran/2406.13469.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.13469.svg)](https://syntology.ai/paper/2406.13469)

Connect an agent — have() is free.