Browse State-of-the-Art › Toxic Comment Classification
Toxic Comment Classification
13 papers with code · 4 benchmarks · 7 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Civil Comments (22 rows) | RoBERTa Focal Loss | A benchmark for toxic comment classification on Civil Comments dataset | code | — | Compare |
| CAD (1 row) | ContextRNN | Revisiting Contextual Toxicity Detection in Conversations | — | — | Compare |
| GermEval 2021 - Toxic Comments test set (1 row) | GBERT/GELECTRA Ensemble | FHAC at GermEval 2021: Identifying German toxic, engaging, and... | code | — | Compare |
| Jigsaw Toxic Comment Classification Dataset (1 row) | CapsNet | Evaluating The Effectiveness of Capsule Neural Network in Toxic... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
7 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 28 · with a code link: 13 · where Syntology ran a sample: 3 (1 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 28 tagged: 1 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 28 of 28, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
1 Jul 2024 1 repository listedAI regulations are expected to prohibit machine learning models from using sensitive attributes during training.
-
31 Mar 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data.
-
12 Oct 2023 1 repository listedBy comparing the performance of CapsNet to that of other architectures, such as DistilBERT, Vanilla Neural Networks (VNN), and Convolutional Neural Networks (CNN), we were able to achieve an accuracy of 90.
-
19 May 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)Unlike these models, humans typically utilize external tools to cross-check and refine their initial content, like using a search engine for fact-checking, or a code interpreter for debugging.
-
26 Jan 2023 1 repository listedBiLSTM remains a good compromise between performance and inference time.
-
7 Sep 2021 1 repository listedThe availability of language representations learned by large pretrained neural network models (such as BERT and ELECTRA) has led to improvements in many downstream Natural Language Processing tasks in recent years.
-
1 Aug 2021 1 repository listedWith the rise of research on toxic comment classification, more and more annotated datasets have been released.
-
1 Dec 2020 1 repository listedAdversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans.
-
12 Oct 2020 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans.
-
1 Aug 2020 1 repository listedRecent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and…
-
2 Jul 2020 1 repository listedThis paper tackles one of the greatest limitations in Machine Learning: Data Scarcity.
-
7 Jun 2018 1 repository listedA large proportion of online comments present on public domains are constructive, however a significant proportion are toxic in nature.
-
27 Feb 2018 1 repository listedTo justify this decision we choose to compare CNNs against the traditional bag-of-words approach for text analysis combined with a selection of algorithms proven to be very effective in text classification.
-
Applying LLMs to Active Learning: Towards Cost-Efficient Cross-Task Text Classification without Manually Labeled Data24 Feb 2025 0 repositories listedMachine learning-based classifiers have been used for text classification, such as sentiment analysis, news classification, and toxic comment classification.
-
Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety27 Mar 2023 0 repositories listedThe rapid growth in user generated content on social media has resulted in a significant rise in demand for automated content moderation.
-
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers22 Feb 2022 0 repositories listedOn the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages.
-
A Survey of Toxic Comment Classification Methods13 Dec 2021 0 repositories listedWhile in real life everyone behaves themselves at least to some extent, it is much more difficult to expect people to behave themselves on the internet, because there are few checks or consequences for posting something…
-
Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models25 Nov 2021 0 repositories listedSociodemographic biases are a common problem for natural language processing, affecting the fairness and integrity of its applications.
-
24 Nov 2021 0 repositories listedUnderstanding toxicity in user conversations is undoubtedly an important problem.
-
SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of "Subjectivity" and "Identity Terms"6 Sep 2021 0 repositories listedToxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as "Muslim" and "black".
-
DeTox at GermEval 2021: Toxic Comment Classification1 Sep 2021 0 repositories listedIn this work, we present our approaches on the toxic comment classification task (subtask 1) of the GermEval 2021 Shared Task.
-
IRCologne at GermEval 2021: Toxicity Classification1 Sep 2021 0 repositories listedIn this paper, we describe the TH Köln’s submission for the Shared Task on the Identification of Toxic Comments at GermEval 2021.
-
Universität Regensburg MaxS at GermEval 2021 Task 1: Synthetic Data in Toxic Comment Classification1 Sep 2021 0 repositories listedWe report on our submission to Task 1 of the GermEval 2021 challenge – toxic comment classification.
-
Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features12 Jun 2021 0 repositories listedDespite the high accuracy offered by state-of-the-art deep natural-language models (e.g. LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user.
-
Vietnamese Complaint Detection on E-Commerce Websites24 Apr 2021 0 repositories listedCustomer product reviews play a role in improving the quality of products and services for business organizations or their brands.
-
18 Mar 2021 0 repositories listedThe rise of social media has led to the increasing of comments on online forums.
-
Detecting Aggression and Toxicity using a Multi Dimension Capsule Network1 Aug 2019 0 repositories listedIn the era of social media, hate speech, trolling and verbal abuse have become a common issue.
-
Challenges for Toxic Comment Classification: An In-Depth Error Analysis20 Sep 2018 0 repositories listedToxic comment classification has become an active research field with many recently proposed approaches.
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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