Paper Citation Record · LEDGER

Test-Time Detoxification without Training or Learning Anything

As of 18 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 1 inbound Pith citation observation for arXiv:2602.02498.

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

pith.paper-citation-record.v1
2602.02498 v2

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T10:40:48.791843Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-25T04:55:34.529357Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T04:56:38.824910Z

Reference resolution

56 of 56 outbound references displayed

verified exact8
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier3
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5fbec80c-406f-45c5-8abe-ebf68d20837b · outbound

This paper cites Llama 3 model card.

Test-Time Detoxification without Training or Learning Anything Llama 3 model card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:42.806327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28332af-9338-440b-89fb-b20c1817cd09 · outbound

This paper cites Director: Generator-classifiers for supervised language modeling.

Test-Time Detoxification without Training or Learning Anything Director: Generator-classifiers for supervised language modeling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:42.906428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeb2f311-d67a-4273-a35a-c0e940209cf1 · outbound

This paper cites Systematic rectification of language models via dead-end analysis.

Test-Time Detoxification without Training or Learning Anything Systematic rectification of language models via dead-end analysis

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.138049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d694e5-1eec-47ff-9527-f509d12f15c6 · outbound

This paper cites Enhancing zeroth-order fine- tuning for language models with low-rank structures.

Test-Time Detoxification without Training or Learning Anything Enhancing zeroth-order fine- tuning for language models with low-rank structures

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.238194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e96ec4-ced7-4fe6-971a-43c9d65c1c71 · outbound

This paper cites Plug and play language models: A simple approach to controlled text generation.

Test-Time Detoxification without Training or Learning Anything Plug and play language models: A simple approach to controlled text generation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.498895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd67719c-dd48-46c0-9c99-8017865f3d2b · outbound

This paper cites Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model.

Test-Time Detoxification without Training or Learning Anything Reward-augmented decoding: Efficient controlled text generation with a unidirectional reward model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.632600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 502b7096-03f6-4cd4-a7d2-45c6438fa9b8 · outbound

This paper cites Bold: Dataset and metrics for measuring biases in open-ended language generation.

Test-Time Detoxification without Training or Learning Anything Bold: Dataset and metrics for measuring biases in open-ended language generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.705903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cc1a41-5dae-4ff5-946a-059a6481c78e · outbound

This paper cites DSCD: Large lan- guage model detoxification with self-constrained decoding.

Test-Time Detoxification without Training or Learning Anything DSCD: Large lan- guage model detoxification with self-constrained decoding

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.810434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a17d23-64c3-49a0-a178-c7900e578e85 · outbound

This paper cites Variance- reduced zeroth-order methods for fine-tuning language models.

Test-Time Detoxification without Training or Learning Anything Variance- reduced zeroth-order methods for fine-tuning language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.896219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d51cb23-83d6-4276-9097-909f18453f2b · outbound

This paper cites an unresolved cited work.

Test-Time Detoxification without Training or Learning Anything Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:43.943014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157e485f-4594-47b7-b2d2-a0ad8553583e · outbound

This paper cites an unresolved cited work.

Test-Time Detoxification without Training or Learning Anything Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.004827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579e2b8e-6328-4685-a7f4-fb1084a74cba · outbound

This paper cites Word embeddings are steers for language models.

Test-Time Detoxification without Training or Learning Anything Word embeddings are steers for language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.121222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae82e7b5-6a7e-458a-af24-06451250ab3b · outbound

This paper cites Detoxify.

Test-Time Detoxification without Training or Learning Anything Detoxify

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.209549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c83bf68-9162-4578-a80f-6f67eecf91f2 · outbound

This paper cites Model-free learning of two-stage beamformers for passive irs-aided network design.IEEE Transactions on Signal Processing, 72:652–669,.

Test-Time Detoxification without Training or Learning Anything Model-free learning of two-stage beamformers for passive irs-aided network design.IEEE Transactions on Signal Processing, 72:652–669,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.273656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 084e3342-62b1-4270-8b5f-d95c109b1374 · outbound

This paper cites Localized zeroth-order prompt optimization.

Test-Time Detoxification without Training or Learning Anything Localized zeroth-order prompt optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.504047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0729dc6-e052-41f2-9071-10a9d4987397 · outbound

This paper cites DAPI: Domain adaptive toxicity probe vector intervention, for fine-grained detoxification.

Test-Time Detoxification without Training or Learning Anything DAPI: Domain adaptive toxicity probe vector intervention, for fine-grained detoxification

Reference 18

Resolution: verified exact; doi, observed 2026-08-03T10:43:24.692646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7a283070-9e23-43dd-8b09-b98104127966 · outbound

This paper cites Perspective API.

Test-Time Detoxification without Training or Learning Anything Perspective API

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.720686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64ae9e1a-f551-42df-af01-c3b013650296 · outbound

This paper cites Critic- guided decoding for controlled text generation.

Test-Time Detoxification without Training or Learning Anything Critic- guided decoding for controlled text generation

Reference 20

Resolution: malformed identifier; no resolver link, observed 2026-08-03T10:40:44.795718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5dc989-3cd5-4410-b345-4148f91f3df4 · outbound

This paper cites Large language models can become strong self- detoxifiers.

Test-Time Detoxification without Training or Learning Anything Large language models can become strong self- detoxifiers

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.873491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 955af843-20b7-4da8-be3a-be83c641809f · outbound

This paper cites Unveiling safety vulnerabilities of large language models.

Test-Time Detoxification without Training or Learning Anything Unveiling safety vulnerabilities of large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.964749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 216f01e5-d833-448e-8418-0bbfaa8a4875 · outbound

This paper cites GeDi: Generative discriminator guided sequence generation.

Test-Time Detoxification without Training or Learning Anything GeDi: Generative discriminator guided sequence generation

Reference 23

Resolution: malformed identifier; no resolver link, observed 2026-08-03T10:40:45.034797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 605f244e-891a-47da-90f4-c4ce37916eee · outbound

This paper cites Language detoxification with attribute- discriminative latent space.

Test-Time Detoxification without Training or Learning Anything Language detoxification with attribute- discriminative latent space

Reference 24

Resolution: verified exact; doi, observed 2026-08-03T10:43:24.522898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b64555ad-df0f-49e1-b4c4-41dd3838165e · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Test-Time Detoxification without Training or Learning Anything Gonzalez, Hao Zhang, and Ion Stoica

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.281879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03923ffc-0057-44f5-818f-6a76c4982658 · outbound

This paper cites Self-detoxifying language models via toxification reversal.

Test-Time Detoxification without Training or Learning Anything Self-detoxifying language models via toxification reversal

Reference 26

Resolution: verified exact; doi, observed 2026-08-03T10:43:24.384596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b6fe4ba-a631-48d5-bb9b-a5a7da976b39 · outbound

This paper cites Destein: Navigating detoxification of language models via universal steering pairs and head-wise activation fusion.

Test-Time Detoxification without Training or Learning Anything Destein: Navigating detoxification of language models via universal steering pairs and head-wise activation fusion

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.485812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8f252cd-af32-4401-a721-52cd7ffecaaf · outbound

This paper cites Smith, and Yejin Choi.

Test-Time Detoxification without Training or Learning Anything Smith, and Yejin Choi

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.652959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd5990ec-16a9-4d5c-a7ae-baa7eb3ebede · outbound

This paper cites Sparse meZO: Less parameters for better performance in zeroth-order LLM fine-tuning.

Test-Time Detoxification without Training or Learning Anything Sparse meZO: Less parameters for better performance in zeroth-order LLM fine-tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.693911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb77aae4-d392-4731-84e4-66f8aacb8cb4 · outbound

This paper cites Unidetox: Universal detoxification of large language models via dataset distillation.

Test-Time Detoxification without Training or Learning Anything Unidetox: Universal detoxification of large language models via dataset distillation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.743033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f767a2fb-0b8d-4c35-a484-3ae8ee2cd770 · outbound

This paper cites Quark: controllable text generation with reinforced [un]learning.

Test-Time Detoxification without Training or Learning Anything Quark: controllable text generation with reinforced [un]learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.851721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19ddedc-2011-4def-a7ff-80975d070efa · outbound

This paper cites Lee, Danqi Chen, and Sanjeev Arora.

Test-Time Detoxification without Training or Learning Anything Lee, Danqi Chen, and Sanjeev Arora

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:45.887597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18635821-dc52-44cf-91a3-a9e391d55e05 · outbound

This paper cites Attribute controlled fine-tuning for large language models: A case study on detoxification.

Test-Time Detoxification without Training or Learning Anything Attribute controlled fine-tuning for large language models: A case study on detoxification

Reference 34

Resolution: verified exact; doi, observed 2026-08-03T10:43:24.244761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d0402cb6-c075-4fd6-b094-65439c0de751 · outbound

This paper cites Random gradient-free minimization of convex functions.

Test-Time Detoxification without Training or Learning Anything Random gradient-free minimization of convex functions

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.020125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ddaa856-8604-4f4a-9c8f-448347729a39 · outbound

This paper cites Parameter-efficient detoxification with contrastive decoding.

Test-Time Detoxification without Training or Learning Anything Parameter-efficient detoxification with contrastive decoding

Reference 36

Resolution: verified exact; doi, observed 2026-08-03T10:43:24.076472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f91f805c-fd2f-4e6e-968d-695a278c72ad · outbound

This paper cites Best practices for prompt engineering with the openai api.

Test-Time Detoxification without Training or Learning Anything Best practices for prompt engineering with the openai api

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.191848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8387a427-3026-4492-953a-d608a990e76b · outbound

This paper cites Training language models to follow instructions with human feed- back.

Test-Time Detoxification without Training or Learning Anything Training language models to follow instructions with human feed- back

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.307849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 005b707d-c3a5-4a33-a28c-d496456cc20a · outbound

This paper cites Data-driven learning of two-stage beamformers in passive irs-assisted systems with inexact oracles.IEEE Access, 13:154984–155002, 2025.

Test-Time Detoxification without Training or Learning Anything Data-driven learning of two-stage beamformers in passive irs-assisted systems with inexact oracles.IEEE Access, 13:154984–155002, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.421898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 611a6e23-6b04-4b48-bae3-f7ad91613cc7 · outbound

This paper cites On the challenges of using black-box APIs for toxicity evaluation in research.

Test-Time Detoxification without Training or Learning Anything On the challenges of using black-box APIs for toxicity evaluation in research

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.579704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f6cee7-372e-4440-9cea-f43ca655ad48 · outbound

This paper cites Language models are unsupervised multitask learners.

Test-Time Detoxification without Training or Learning Anything Language models are unsupervised multitask learners

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.741625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c12e80fd-9820-4537-b43a-468bc9c0e001 · outbound

This paper cites Compatible Gradient Approximations for Actor-Critic Algorithms.

Test-Time Detoxification without Training or Learning Anything Compatible Gradient Approximations for Actor-Critic Algorithms

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.798099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b4258fc-5a6a-4a57-8ae7-aee8bceed33b · outbound

This paper cites Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp.Transactions of the Association for Computational Linguistics, 9: 1408–1424, 12 2021.

Test-Time Detoxification without Training or Learning Anything Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp.Transactions of the Association for Computational Linguistics, 9: 1408–1424, 12 2021

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.850563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a9f0f6-951a-4c6c-a1f9-cf09c97b08c6 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Test-Time Detoxification without Training or Learning Anything Gemma 2: Improving Open Language Models at a Practical Size

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:46.882802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7db505d2-cf81-445a-96a0-51a605765a09 · outbound

This paper cites Supporting Human Raters with the Detection of Harmful Content Using Large Language Models.

Test-Time Detoxification without Training or Learning Anything Supporting Human Raters with the Detection of Harmful Content Using Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:47.108176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0fda032-79be-4c75-9c97-1bdff3970190 · outbound

This paper cites Attention is all you need.

Test-Time Detoxification without Training or Learning Anything Attention is all you need

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:47.258215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6608bb6-3a5a-4bf5-8d19-502254983ebc · outbound

This paper cites Exploring the limits of domain-adaptive training for detoxifying large-scale language models.

Test-Time Detoxification without Training or Learning Anything Exploring the limits of domain-adaptive training for detoxifying large-scale language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:47.413277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 068f988c-52e5-4efc-9fdc-96c9f8aefab7 · outbound

This paper cites Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report.

Test-Time Detoxification without Training or Learning Anything Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:47.652225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a1f4783-4ead-4eb8-9fa3-2ddf13ed13a2 · outbound

This paper cites Challenges in detoxifying language models.

Test-Time Detoxification without Training or Learning Anything Challenges in detoxifying language models

Reference 49

Resolution: verified exact; doi, observed 2026-08-03T10:43:23.959123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ea4d298d-36ed-452f-a225-8b5ed21fe92d · outbound

This paper cites an unresolved cited work.

Test-Time Detoxification without Training or Learning Anything Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:47.969024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30a5345-9c90-4959-a990-ed83e702c121 · outbound

This paper cites Recipes for Safety in Open-domain Chatbots.

Test-Time Detoxification without Training or Learning Anything Recipes for Safety in Open-domain Chatbots

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:48.133852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06bb1a45-8d5d-4ac7-85b0-c841b522d2e5 · outbound

This paper cites SafeDecoding: Defending against jailbreak attacks via safety-aware decoding.

Test-Time Detoxification without Training or Learning Anything SafeDecoding: Defending against jailbreak attacks via safety-aware decoding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:48.239022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f86dc234-3023-4839-8f86-4b978e448fd0 · outbound

This paper cites Qwen3 Technical Report.

Test-Time Detoxification without Training or Learning Anything Qwen3 Technical Report

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:48.406588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 836aad66-9385-4267-ab9a-c0498fe189bf · outbound

This paper cites doi: 10.18653/v1/2024.acl-long.303.

Test-Time Detoxification without Training or Learning Anything doi: 10.18653/v1/2024.acl-long.303

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:48.360785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f576f16-a0d8-4fca-8992-9dfa7bcc1f9d · outbound

This paper cites Unlocking black-box prompt tuning efficiency via zeroth-order optimization.

Test-Time Detoxification without Training or Learning Anything Unlocking black-box prompt tuning efficiency via zeroth-order optimization

Reference 55

Resolution: malformed identifier; no resolver link, observed 2026-08-03T10:40:48.581549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e91581-2346-4096-90cc-4fe25c9bcce4 · outbound

This paper cites FUDGE: Controlled text generation with future discriminators.

Test-Time Detoxification without Training or Learning Anything FUDGE: Controlled text generation with future discriminators

Reference 56

Resolution: verified exact; doi, observed 2026-08-03T10:43:23.852656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3e9072a0-91cb-4d51-8f1b-19ca041561a0 · outbound

This paper cites challenging.

Test-Time Detoxification without Training or Learning Anything challenging

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:48.791843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34348249-bd37-40b0-8a86-671f35d610f6 · outbound

This paper cites Detoxifying large language models via the diversity of toxic samples.

Test-Time Detoxification without Training or Learning Anything Detoxifying large language models via the diversity of toxic samples

Reference 58

Resolution: verified exact; doi, observed 2026-08-03T10:43:23.746647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7ef13665-fc61-4fb2-9cff-e194a52b1c7f · outbound

This paper cites an unresolved cited work.

Test-Time Detoxification without Training or Learning Anything Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T10:40:44.411215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4ef9a461-ef0a-4c98-845a-2a15d2b6f4fe · inbound

Self-Improving In-Context Learning cites this paper.

Self-Improving In-Context Learning Test-Time Detoxification without Training or Learning Anything

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-30T02:16:14.044451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.