Browse State-of-the-Art › Hate Speech Detection

Hate Speech Detection

203 papers with code · 15 benchmarks · 47 datasets archive 2025-07-28

Natural Language Processing

Hate speech detection is the task of detecting if communication such as text, audio, and so on contains hatred and or encourages violence towards a person or a group of people. This is usually based on prejudice against 'protected characteristics' such as their ethnicity, gender, sexual orientation, religion, age et al. Some example benchmarks are ETHOS and HateXplain. Models can be evaluated with metrics like the F-score or F-measure.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 15 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. 10 shown of 15 until expanded.

Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): HateMM (1 judged, 0 placed), OLID (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Ethos Binary (12 rows) BiLSTM + static BE Hate speech detection using static BERT embeddings — — Compare
HateXplain (11 rows) BERT-MRP Why Is It Hate Speech? Masked Rationale Prediction for Explainable... code 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) · 0 unverified Compare
Ethos MultiLabel (5 rows) MLARAM ETHOS: an Online Hate Speech Detection Dataset code — Compare
Waseem et al., 2018 (3 rows) Mozafari et al., 2019 AAA: Fair Evaluation for Abuse Detection Systems Wanted code — Compare
AbusEval (2 rows) HateBERT HateBERT: Retraining BERT for Abusive Language Detection in English code — Compare
Automatic Misogynistic Identification (2 rows) mBert Deep Learning Models for Multilingual Hate Speech Detection code — Compare
HateMM (2 rows) HXP + CLAP + CLIP Towards a Robust Framework for Multimodal Hate Detection: A Study... code — Compare
HatEval (2 rows) HateBERT HateBERT: Retraining BERT for Abusive Language Detection in English code — Compare
OffensEval 2019 (2 rows) HateBERT HateBERT: Retraining BERT for Abusive Language Detection in English code — Compare
ToLD-Br (2 rows) Multilingual BERT Toxic Language Detection in Social Media for Brazilian Portuguese:... code — Compare
bajer_danish_misogyny (1 row) AOM mBERT Annotating Online Misogyny code — Compare
DKhate (1 row) Baseline Offensive Language and Hate Speech Detection for Danish — — Compare
Hostility Detection Dataset in Hindi (1 row) Auxiliary IndicBert Hostility Detection in Hindi leveraging Pre-Trained Language Models code — Compare
OLID (1 row) RoBERTa-large-ST Noisy Self-Training with Data Augmentations for Offensive and Hate... code — Compare
SHAJ (1 row) Baseline BERT (task A) Detecting Abusive Albanian — — 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

47 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 47 until expanded.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 507 · with a code link: 203 · where Syntology ran a sample: 17 (11 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (17 of 507 tagged: 11 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 6: papers 1 to 100 of 507, 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. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 12 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