Paper Citation Record · LEDGER

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments

As of 8 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 2 inbound Pith citation observations for arXiv:2505.18927.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.18927 v3

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:26:06.079416Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:40:53.518319Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

44 of 44 outbound references displayed

verified exact11
verified fuzzy5
unresolved25
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 5db965e9-7c15-4a5d-b0d5-2094c234cf31 · outbound

This paper cites Social media usage & growth statistics,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Social media usage & growth statistics,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:09.997086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8df92432-dba0-47d5-941e-f116215d64d4 · outbound

This paper cites Study of cyberbullying among adoles- cents in recent years: A bibliometric analysis,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Study of cyberbullying among adoles- cents in recent years: A bibliometric analysis,

Reference 2

Resolution: verified exact; doi, observed 2026-08-07T14:26:07.391640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18b8e6d9-a4a9-4f13-8b1d-426de451b2de · outbound

This paper cites Bullying, cyberbullying, and sui- cide,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Bullying, cyberbullying, and sui- cide,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:01.772732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686ff8d2-7d00-4358-b40d-c1a5c6de529e · outbound

This paper cites Anonymously hurting others online: The effect of anonymity on cyberbullying frequency,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Anonymously hurting others online: The effect of anonymity on cyberbullying frequency,

Reference 4

Resolution: verified exact; doi, observed 2026-08-07T14:26:07.290788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 157579ce-d39b-4d6c-8935-180997321ba0 · outbound

This paper cites The severity of cyberbullying affects bystander inter- vention among college students: The roles of feelings of responsibility and empathy,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments The severity of cyberbullying affects bystander inter- vention among college students: The roles of feelings of responsibility and empathy,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:09.741821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 99476d24-ca87-4325-a8a8-a0d1092d6f1c · outbound

This paper cites Cyberbullying: Twenty crucial statistics for 2024,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Cyberbullying: Twenty crucial statistics for 2024,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:09.637873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac46b7e6-beaf-408f-823c-a10db7016479 · outbound

This paper cites Social media use and cyber-bullying: A cross-national analysis of young people in 42 countries,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Social media use and cyber-bullying: A cross-national analysis of young people in 42 countries,

Reference 7

Resolution: verified exact; doi, observed 2026-08-07T14:26:07.070621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bef6880a-f508-424d-92cb-ac210bbea04c · outbound

This paper cites Automated content moderation increases adherence to community guidelines,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Automated content moderation increases adherence to community guidelines,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:02.603283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1908ea43-7680-459c-a77c-929e9c54dac1 · outbound

This paper cites Content moderation on social media: Does it matter who and why moderates hate speech?.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Content moderation on social media: Does it matter who and why moderates hate speech?

Reference 9

Resolution: verified exact; raw_fallback, observed 2026-08-07T14:26:09.126475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0b12bd2f-f4d2-48be-9831-ba923a98b510 · outbound

This paper cites Content moderation, AI, and the question of scale,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Content moderation, AI, and the question of scale,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:02.838515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 356e7bbc-bb15-4910-9445-44587fc4f100 · outbound

This paper cites Context in abusive language detection: On the interdependence of context and annotation of user comments,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Context in abusive language detection: On the interdependence of context and annotation of user comments,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:02.959353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e62026b0-8528-4034-865d-ab830ac5aad5 · outbound

This paper cites Relationship between peer victimization, cyberbullying, and suicide in children and adolescents: A meta-analysis,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Relationship between peer victimization, cyberbullying, and suicide in children and adolescents: A meta-analysis,

Reference 12

Resolution: verified exact; raw_fallback, observed 2026-08-07T14:26:08.845913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 64eec8d1-f6cc-4dbe-ab94-5746b565a626 · outbound

This paper cites Hateful symbols or hateful people? Predic- tive features for hate speech detection on Twitter,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Hateful symbols or hateful people? Predic- tive features for hate speech detection on Twitter,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.184731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9669003d-c656-4ca4-be7f-5868dc6b247d · outbound

This paper cites Large scale crowdsourcing and characterization of Twitter abusive behavior,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Large scale crowdsourcing and characterization of Twitter abusive behavior,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.262070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cc693c-b755-48fd-be3d-70646fde654e · outbound

This paper cites Predicting the type and target of offensive posts in social media,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Predicting the type and target of offensive posts in social media,

Reference 15

Resolution: verified exact; doi, observed 2026-08-07T14:26:06.937372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 08c23833-3bb5-42aa-a356-064b4ad46540 · outbound

This paper cites HateCheck: Functional tests for hate speech detection models,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments HateCheck: Functional tests for hate speech detection models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.465498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837578b0-eaf1-4e26-9fb4-a3a74a7dbd0f · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments BERT: Pre-training of deep bidirectional transformers for language understanding,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.578156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a434f05-2bad-4c10-9367-53deacbd5d63 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.718173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d0edd2-d4a5-41b5-82f4-156a04eec678 · outbound

This paper cites HateXplain: A benchmark dataset for explainable hate speech detection,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments HateXplain: A benchmark dataset for explainable hate speech detection,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.835381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9babcd5e-2770-4783-81e5-1d05cbbb1433 · outbound

This paper cites Learning from the worst: Dynamically generated datasets to improve online hate detection,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Learning from the worst: Dynamically generated datasets to improve online hate detection,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:03.956300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ff1c27-5f5d-4cec-ae8a-dd3afc4ab969 · outbound

This paper cites RealToxicityPrompts: Evaluating neural toxic degeneration in language models,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments RealToxicityPrompts: Evaluating neural toxic degeneration in language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.057458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002eb337-b319-41a7-8873-5f6a634a534e · outbound

This paper cites Sarcasm detection in social media: A review,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Sarcasm detection in social media: A review,

Reference 22

Resolution: verified exact; doi, observed 2026-08-07T14:26:06.797242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0dcf14c3-5208-4fb5-897c-3d5e600601eb · outbound

This paper cites A systematic review of hate speech automatic detection using natural language processing,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments A systematic review of hate speech automatic detection using natural language processing,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.199326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5227cf14-51a1-473b-8986-357a34234215 · outbound

This paper cites Assessing the impact of contextual information in hate speech detection,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Assessing the impact of contextual information in hate speech detection,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.253570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15c3a7fe-9817-446b-9529-027c067e5482 · outbound

This paper cites Abusive language detection on Arabic social media,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Abusive language detection on Arabic social media,

Reference 25

Resolution: malformed identifier; no resolver link, observed 2026-08-07T14:26:04.321163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0980ef36-ab44-4844-bf5b-e8fd744e6ed6 · outbound

This paper cites Overview of the HASOC track at FIRE 2019: Hate speech and offensive content identification in Indo-European languages,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Overview of the HASOC track at FIRE 2019: Hate speech and offensive content identification in Indo-European languages,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.466119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7632815-ab2b-4ee7-a221-70b4f161eb5c · outbound

This paper cites 'All you need is Love': Evading hate speech detection,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments 'All you need is Love': Evading hate speech detection,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.618556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90122017-13a9-4b03-92de-14974c0336af · outbound

This paper cites Transliteration for cross-lingual morphological inflection,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Transliteration for cross-lingual morphological inflection,

Reference 28

Resolution: malformed identifier; doi_truncated, observed 2026-08-07T14:26:06.669181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 461a042e-0b00-4a33-aa97-ce0aa9610262 · outbound

This paper cites GLUECoS: An evaluation benchmark for code-switched NLP,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments GLUECoS: An evaluation benchmark for code-switched NLP,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.837575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85632d0e-a5a3-4c66-b90c-caf1515e3e6f · outbound

This paper cites Multilingual offensive language identi- fication with cross-lingual embeddings,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Multilingual offensive language identi- fication with cross-lingual embeddings,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:04.988049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a31d7bb-3c6d-4d7a-9c9a-4efb3c392ddf · outbound

This paper cites A corpus of Turkish offensive language on social media,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments A corpus of Turkish offensive language on social media,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:09.506277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1244498c-2f31-4677-9652-9272f452d02b · outbound

This paper cites Cross-domain and cross-lingual abusive language detection: A hybrid approach with deep learning and a mul- tilingual lexicon,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Cross-domain and cross-lingual abusive language detection: A hybrid approach with deep learning and a mul- tilingual lexicon,

Reference 32

Resolution: verified exact; doi, observed 2026-08-07T14:26:06.515058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d9c80a32-06a0-458b-b701-46a0664c3c2d · outbound

This paper cites LLM-Mod: Can Large Language Models Assist Content Moderation?.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments LLM-Mod: Can Large Language Models Assist Content Moderation?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.353460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e92b07-8e28-4c92-889a-8fc641057a9a · outbound

This paper cites Respectful or toxic? Using zero-shot learning with language models to detect hate speech,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Respectful or toxic? Using zero-shot learning with language models to detect hate speech,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.442107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 764d5622-66e8-4c83-9d40-c668610aa916 · outbound

This paper cites Toxicity detection: Does context really matter?.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Toxicity detection: Does context really matter?

Reference 35

Resolution: malformed identifier; no resolver link, observed 2026-08-07T14:26:05.554225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425aba53-7f9c-44ca-a3f1-254d1706d36c · outbound

This paper cites Just say no: Analyzing the stance of neural dialogue generation in offensive contexts,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Just say no: Analyzing the stance of neural dialogue generation in offensive contexts,

Reference 36

Resolution: verified exact; doi, observed 2026-08-07T14:26:06.365345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c52ab4e6-b122-4ec0-9ad0-e97775b4dec4 · outbound

This paper cites Social bias frames: Reasoning about social and power implications of language,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Social bias frames: Reasoning about social and power implications of language,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.760493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eac49d29-b41d-4565-bbd6-d1c32a74ab97 · outbound

This paper cites Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.832029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b6a99e-7ebe-46e4-9ad6-52193ad5733a · outbound

This paper cites Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.879394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76698800-6522-4e0e-aaad-01e1f260eb78 · outbound

This paper cites Challenges in Detoxifying Language Models.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Challenges in Detoxifying Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:05.971383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eeaaf62-9549-4a05-9ef8-32773a3c651c · outbound

This paper cites Toxigen: Controllable generation of implicit and adversarial toxic text,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Toxigen: Controllable generation of implicit and adversarial toxic text,

Reference 41

Resolution: verified exact; doi, observed 2026-08-07T14:26:06.231838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 13abb845-0799-4a32-88bb-a41170490c5e · outbound

This paper cites On the dangers of stochastic parrots,.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments On the dangers of stochastic parrots,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:06.079416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a542b556-d4c0-49ad-a5ce-e6f141396938 · outbound

This paper cites an unresolved cited work.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Unresolved cited work

Reference 2023

Resolution: verified exact; doi, observed 2026-08-07T14:26:07.149627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8449c10b-0861-4455-91de-201f4781a5c1 · outbound

This paper cites Available: https://backlinko.com/social-media-users.

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments Available: https://backlinko.com/social-media-users

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:26:09.842514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 99dde630-bd75-44df-a79e-0b34943d0439 · inbound

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages cites this paper.

Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:40:53.518319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c5e3b8-5b06-42eb-b9fa-a242f4663d64 · inbound

Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention cites this paper.

Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments

Reference 151

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:13:44.409956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.