Paper Citation Record · LEDGER

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content

As of 18 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2504.16120.

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

pith.paper-citation-record.v1
2504.16120 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:57:58.481821Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

29 of 29 outbound references displayed

verified exact1
verified fuzzy8
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a36507a3-bce5-4285-9dd6-c4f21cec32a5 · outbound

This paper cites HateBERT: Retraining BERT for Abusive Language Detection in English.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content HateBERT: Retraining BERT for Abusive Language Detection in English

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.349909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320e32b3-3abb-4d98-bc45-50e738c89da4 · outbound

This paper cites Generalizable implicit hate speech detection using contrastive learning.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Generalizable implicit hate speech detection using contrastive learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:59.009796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 336e58c1-2cfe-4d1c-bf3d-e07727761498 · outbound

This paper cites Toxicity Detection with Generative Prompt-based Inference.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Toxicity Detection with Generative Prompt-based Inference

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.360079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60bfc48d-daeb-4c23-ad37-d75bc4ece791 · outbound

This paper cites Interpretable Unified Language Checking.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Interpretable Unified Language Checking

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.365238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 942e92d9-3e44-4cee-9252-678314e1b8dd · outbound

This paper cites Efficient toxic content detection by bootstrapping and distilling large language models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Efficient toxic content detection by bootstrapping and distilling large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.994057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0f16f588-b224-4399-9ac9-37a9e14e03e0 · outbound

This paper cites Autorag-hp: Automatic online hyper-parameter tuning for retrieval-augmented generation, 2024.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Autorag-hp: Automatic online hyper-parameter tuning for retrieval-augmented generation, 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.978221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d7aff224-a7f6-4137-bc57-64d541e29bb4 · outbound

This paper cites Enhancing rag-retrieval to improve llms robustness and resilience to hallucinations.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Enhancing rag-retrieval to improve llms robustness and resilience to hallucinations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.962628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6e635869-fc1b-4e51-9553-e43277539d36 · outbound

This paper cites Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.384880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a57a7fb-b546-4e15-8b5f-fdb0cdd21f80 · outbound

This paper cites Principle-driven self-alignment of language models from scratch with minimal human supervision.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Principle-driven self-alignment of language models from scratch with minimal human supervision

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.943906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e9d6f8f8-ada5-48c8-a1c8-67027b085e5d · outbound

This paper cites Large Language Models Can Self-Improve.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Large Language Models Can Self-Improve

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.393817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12df2720-929c-498a-81d4-be70bc9e27c2 · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Defending chatgpt against jailbreak attack via self-reminders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.398683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 328eb7db-aa73-4019-a1bb-2600609ff86d · outbound

This paper cites Learning and Forgetting Unsafe Examples in Large Language Models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Learning and Forgetting Unsafe Examples in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.403124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d057b93d-707c-4f3e-83be-681ddef8f05f · outbound

This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.408251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4efc1b79-49e9-43bd-983c-8110d327362b · outbound

This paper cites N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.413300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5dafa0f-1739-4a33-8471-f128150f9b1e · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Self-refine: Iterative refinement with self-feedback

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.418083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c951aff8-9d27-4c74-b26c-0e1abec7eba9 · outbound

This paper cites Learning From Mistakes Makes LLM Better Reasoner.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Learning From Mistakes Makes LLM Better Reasoner

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.422905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e95c6c9-21bd-4feb-aa81-0e9731522847 · outbound

This paper cites On the Intersection of Self-Correction and Trust in Language Models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content On the Intersection of Self-Correction and Trust in Language Models

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:57:58.668317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bdca6dd3-a4ea-485b-8a01-8c25ffec1435 · outbound

This paper cites Self-correcting LLM-controlled Diffusion Models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Self-correcting LLM-controlled Diffusion Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.432298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62211133-2455-4a2c-8fb3-50b068d890d2 · outbound

This paper cites Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.436976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a84671f-7d73-4341-97fa-7a785fc02f8a · outbound

This paper cites SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.441508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92cceca0-5f6a-4e54-9951-7ad63ac85a96 · outbound

This paper cites Large Language Models Cannot Self-Correct Reasoning Yet.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Large Language Models Cannot Self-Correct Reasoning Yet

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.445879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f6f01b-3dcc-4f2e-8df2-e8216a911a56 · outbound

This paper cites Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.450689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a9de15-d9ee-471a-b5a3-04297d85cda3 · outbound

This paper cites Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.455088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ebb4933-f62b-4d22-8a2f-3e5ab959c992 · outbound

This paper cites Model editing as a robust and denoised variant of dpo: A case study on toxicity.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Model editing as a robust and denoised variant of dpo: A case study on toxicity

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.898336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0024866d-96ea-4474-9adb-00402ab5ab4a · outbound

This paper cites Gpt-4 technical report, 2024.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Gpt-4 technical report, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.882566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 413fb6e2-2ebb-419e-a05c-91442c24af35 · outbound

This paper cites Dai, and Orhan Firat et al.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Dai, and Orhan Firat et al

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:57:58.865315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f7858d28-88a2-4eba-b66d-39c88436ce30 · outbound

This paper cites Mistral 7B.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Mistral 7B

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.473001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a28d03b-e9d8-44c7-bc94-f7f4a124058a · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Gemma: Open Models Based on Gemini Research and Technology

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:57:58.477590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 688c89b4-8cd8-42db-bd51-d31a57780f21 · outbound

This paper cites an unresolved cited work.

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:57:58.848246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

No inbound Pith citation observations are available.