SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.01778 · 2026

LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction

Nils Hellwig, Jakob Fehle, Udo Kruschwitz, Christian Wolff

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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 0 have no contract verdict; 9 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2603.01778.json · badge: /api/ran/2603.01778.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
NilsHellwig/LA-ABSA canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_mean_scores Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/performance_helper.py
pointer only (licence: NONE) · get_code("f2a932cd755cf3d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

extract_text_between_quotes Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/03_llm_eda_few_shot_augmenter.py
pointer only (licence: NONE) · get_code("6600ec5de8c92cf8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

get_all_terms Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/02_eda_few_shot_augmenter.py
pointer only (licence: NONE) · get_code("1dd81bc0176b38e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

get_prompt Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/03_llm_eda_few_shot_augmenter.py
pointer only (licence: NONE) · get_code("eb03a5076b44c920")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

limit_decimal_points Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/performance_helper.py
pointer only (licence: NONE) · get_code("b5ac14e8024dfbfb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

run_with_timeout Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/01_llm_annotate_train.py
pointer only (licence: NONE) · get_code("94eed63652a6ce70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

simple_tokenizer Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/02_eda_few_shot_augmenter.py
pointer only (licence: NONE) · get_code("f3d27eb259941347")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

split_sentence Ran
ran; our contract draft was wrong, not the code
NilsHellwig/LA-ABSA/01_create_annotated_examples/04_back_translation_few_shot_augmenter.py
pointer only (licence: NONE) · get_code("446caa0b476baa2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

to_array Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
NilsHellwig/LA-ABSA/performance_helper.py
pointer only (licence: NONE) · get_code("93abc20af76804f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NilsHellwig/LA-ABSA when it was checked. 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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.

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

Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach that leverages Large Language Model (LLM)-generated annotations to fine-tune lightweight models for complex ABSA tasks. We evaluate our approach on five datasets for Target Aspect Sentiment Detection (TASD) and Aspect Sentiment Quad Prediction (ASQP). Our approach outperformed previously reported augmentation strategies and achieved competitive performance with LLM-prompting in low-resource scenarios, while providing substantial energy efficiency benefits. For example, using 50 annotated examples for in-context learning (ICL) to guide the annotation of unlabeled data, LA-ABSA achieved an F1 score of 49.85 for ASQP on the SemEval Rest16 dataset, closely matching the performance of ICL prompting with Gemma-3-27B (51.10), while requiring significantly lower computational resources.

For agents

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

get_harvested_code_for_paper("2603.01778")
get_code_for_paper("2603.01778")
have("2603.01778")

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

curl https://syntology.ai/api/ran/2603.01778.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.01778.svg)](https://syntology.ai/paper/2603.01778)

Connect an agent — have() is free.