Pith. sign in

Paper Citation Record · LEDGER

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

As of 8 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2505.17078.

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

pith.paper-citation-record.v1
2505.17078 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:34.927348Z

measured 48 of 48 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-25T21:16:36.392606Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T19:30:07.677913Z

Reference resolution

47 of 47 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved44
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1d306a81-6087-4078-b15e-c9bb30816cd2 · outbound

This paper cites Language Models are Few-Shot Learners.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Language Models are Few-Shot Learners

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:29.664936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:29.664936Z digest=sha256:f00293ad9accdb973479570abf81d351753b6452de17cc9599f40556eb3412e4

Observation f7ea174d-9138-4304-bff3-45199293e2e5 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:29.746753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:29.746753Z digest=sha256:175965313af6824ac86f836782404e08422a2752f3df6791f692cc42658e93aa

Observation 0030270b-98e4-4c25-ba40-54e871ad0c6b · outbound

This paper cites Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:29.873282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:29.873282Z digest=sha256:4eb67530d6c10058762c7a6d4f21513f2a6e950d1afbb6dc105bb9b89da40ab2

Observation 8bc8dc52-34b8-4476-9817-a1d9c6861d66 · outbound

This paper cites Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-08-07T15:42:35.937389Z

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.

source=arxiv_source observed=2026-08-07T15:42:29.987832Z digest=sha256:6e61c3834975eb32922b92e3e32b8ca8fa068fc7a9379dc55c82717d2d14825a

Observation 329266cd-b7eb-4096-baf3-9c10cca7b507 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.146022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.146022Z digest=sha256:9d9a1713770f3a8803641efbfefac4d4ca729140e0802fc32f6911581dc6496c

Observation 39c5fca4-d2dc-4489-847d-39654dee5017 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.234297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.234297Z digest=sha256:968a325083672106cba162f3585ba994b651b9d00caa7d02815d0ff548b6fc28

Observation bf6c5531-3793-4654-8bf7-6ff5ccaa77cc · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.404467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.404467Z digest=sha256:466e91c64f551c6257ed6791637bdd4a3138a1a683a839e3a7ee024ada3701eb

Observation 641ea04d-3d6a-4670-92a9-b9e6ef1cb70b · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Transformer Feed-Forward Layers Are Key-Value Memories

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.575351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.575351Z digest=sha256:3ab108919abb257ce9ddbdb8aa6d426219028a2678203dc1c1e7c02388402d50

Observation d18b0f2a-41c8-422e-8a51-3e892a8222cc · outbound

This paper cites A Survey on LLM-as-a-Judge.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace A Survey on LLM-as-a-Judge

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.761330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.761330Z digest=sha256:5960d87f84c73060e581c513783e81c87d73a5c032b7c3e3e5740bb10bec0c0f

Observation 9c46c601-880b-470b-8d8a-55e33dd258a3 · outbound

This paper cites Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:30.991971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:30.991971Z digest=sha256:bd89f5ff80989066fe6a00e0e5b7cce7bdafb45c0209665e5c148b8a2c97ce2c

Observation ad8fa427-1c89-40f0-a84c-0d01ea855c41 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace LoRA: Low-Rank Adaptation of Large Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.079246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.079246Z digest=sha256:50131ee4c186aef7bde8a37f13aa1d6291f6f050859d6aee1de5d0d2b8b72e37

Observation c9e0a81d-3400-4da3-9421-f438f68c5b97 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.187270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.187270Z digest=sha256:e84c7cb077177795b6a36e2f76646e66c1a40c351e36a81ca102ba1309eb131e

Observation a47f9934-f65f-439d-95bb-433dd09c4b1e · outbound

This paper cites CTRL: A Conditional Transformer Language Model for Controllable Generation.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace CTRL: A Conditional Transformer Language Model for Controllable Generation

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.288935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.288935Z digest=sha256:66d3f4c41b74e7889a832e1100ff040c3eae4c4902b5d095c2d8dd8e55038f36

Observation 51668387-e90c-4c23-9f51-2aa63e824fc6 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.478253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.478253Z digest=sha256:337fec82a364708a3929d4365b27d50269c82bd69563ae001106cb1a4da421e8

Observation be266ba5-146b-4df2-bf88-7669b297273f · outbound

This paper cites Kummerfeld, and Rada Mihalcea.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Kummerfeld, and Rada Mihalcea

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.629100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.629100Z digest=sha256:4fb85aa461cae0996de3e8413b2224980f2b8ad8c3c6c9f1cb83d6a46f6aa6f1

Observation 5458b9a1-d04a-4b6c-8d6f-a3446b74548a · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:31.866816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:31.866816Z digest=sha256:e346f0fbf8af41a3826c46f1962d2958e7ddccdd0c709ddb2bceb580ecb769c5

Observation 923982c6-6001-4ee4-9417-33db731489ac · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.063185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.063185Z digest=sha256:59e395b5279c781eae975a41d251ba40aa8b8da866b3837e23e5a2cae260b3cf

Observation 54f4af7d-478a-4730-a630-eaa271f23cca · outbound

This paper cites How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.247738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.247738Z digest=sha256:ba75c5295f61931e39325d0a671f139638be4e735dde32d0bf3ab20cd7c69f67

Observation f98c7e8c-78dd-4f6e-a4ea-985c269fd065 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.402656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.402656Z digest=sha256:b01e9d88111b7002a04f19b99eea953c397b95273098279bad8537ed9bc9773f

Observation 4a3cf486-9d7b-4c94-a396-953cb1cb176d · outbound

This paper cites Pointer Sentinel Mixture Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Pointer Sentinel Mixture Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.513753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.513753Z digest=sha256:86cb0ca8bac1a9afac8126f9bbc5c33dc9ca59a7ca9ad1303b890feb7161b76f

Observation 1ae10703-9ec0-4440-9443-add8c5e5a0a6 · outbound

This paper cites How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.659490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.659490Z digest=sha256:46e18031c5f57a475d52fc1cd3ac840a701c2eb98cfaa51d80bf8698cf856f9a

Observation b2873002-6487-4545-88ad-cfda3ac77a59 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.737455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.737455Z digest=sha256:1d3e0e5393767a63906cded5c165f6eeed145f77b8d1709b68a851a23e5376f1

Observation 63ed797c-92c4-44b6-b78d-d3a1b93a6163 · outbound

This paper cites The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.812422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.812422Z digest=sha256:060b8bc41739194b2635a2991270513aab1db24a3fabfe80fc85102ac64231ac

Observation c4775586-43ab-4b75-9ed7-cd07cb1fb1b1 · outbound

This paper cites Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning

Reference 24

Resolution
verified exact
local_arxiv, observed 2026-08-07T15:42:35.595656Z

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.

source=arxiv_source observed=2026-08-07T15:42:32.887910Z digest=sha256:ac8ebcda8a020a0ba4bccdf960c802dba680d114455f0e32fc287673642679c3

Observation f3e95b49-3a12-42ec-8797-3fac0f195282 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:32.984503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:32.984503Z digest=sha256:d1bd853987897b8091b23917285691c1e78b05ade56d6d7048ae6aad7ecd8136

Observation 1c257683-16cb-48fb-a62b-a6baca8c13bb · outbound

This paper cites Manning, and Chelsea Finn.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Manning, and Chelsea Finn

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.052940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.052940Z digest=sha256:aec014e0e0e2e55b793d505f4a8a342fefb7fd0e40548b002db010c0e1edfa6f

Observation 3747225d-75ba-47bf-a7c0-81c2fbf4c196 · outbound

This paper cites Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.134548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.134548Z digest=sha256:27b37efd34fe6dacffe39557d6df61ec6fa208b696f19c7b1da0f21430f6b979

Observation aafb8c31-4fb1-4b82-9d73-b1ad8801d2ee · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.226307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.226307Z digest=sha256:4b19bc65f8f163f8df0426cd94d64a2ccb6a842427f523891b3adb9112c3e43f

Observation d7a229c4-804a-43cd-ac26-2a4f81e96d8d · outbound

This paper cites Function Vectors in Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Function Vectors in Large Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.313206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.313206Z digest=sha256:fcacd066cb7c51cc3f07f53ad40223fb1608ec89e0797282adcc920503776541

Observation a342c3a4-e89b-4bca-86f7-afb188ca2318 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:42:36.407052Z

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.

source=arxiv_source observed=2026-08-07T15:42:33.391718Z digest=sha256:8d2897a732bca2fabf2fab69b9d55c6aea87f889fd32db02a5df329bd161b13f

Observation bee9739f-8e95-4919-842f-7b17a6f03b7d · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.486225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.486225Z digest=sha256:67328081325ee89592fa15b4a2097e67f4829ac9f860b25e2305f2ebe5805b4c

Observation 572592ee-afe2-490c-9246-afbd008ec68e · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.593951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.593951Z digest=sha256:e63e657c54280751356a0a031f7df29ba942fb9606ae8813fab41ce052681ab5

Observation caf42a89-8f96-4b7a-b82b-b4f12b28c000 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.684125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.684125Z digest=sha256:7e0635a3cd6dab02ee754ae89f5662948f6a735d1ee3e2b2eb0353a86b7e98b7

Observation e8d5339d-76e1-47eb-8184-3b2997e1852f · outbound

This paper cites MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models

Reference 34

Resolution
verified exact
local_arxiv, observed 2026-08-07T15:42:35.368512Z

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.

source=arxiv_source observed=2026-08-07T15:42:33.775749Z digest=sha256:28a66f106f735b54b180ed8ff7a5324082231c1fcb25d8d43127c00d3704a68b

Observation fa8798e2-dfe8-4a2a-948a-3063f9ce1879 · outbound

This paper cites DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.854739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.854739Z digest=sha256:6ddf858454ab8e0da2380c17d85446c2f3840bc82dda9f1df75ede26f67a176a

Observation 81774b8d-8151-4458-9f5b-abf3727b8984 · outbound

This paper cites SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:33.939169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:33.939169Z digest=sha256:ad02d690a6c1e95fae1d88a82912c389eea2532f6b0103439db3638dda8ee9ee

Observation 63c3cdbe-a1e5-456d-85ec-57ac075670c2 · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.038431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.038431Z digest=sha256:4e967976228d9f9b3f748eb197dfc668c191df3945ec9862d8aff478d623713f

Observation ba919713-722f-441b-acca-c035a371369a · outbound

This paper cites The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.123986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.123986Z digest=sha256:9ec0be4542d464e5121db03935bc18414208ae6a58b98323b0fc1a6081e1952e

Observation b50eff71-d362-4bc0-b505-bbc2919538a1 · outbound

This paper cites Knowledge Circuits in Pretrained Transformers.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Knowledge Circuits in Pretrained Transformers

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.207035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.207035Z digest=sha256:df7ac68231d2431660e9fca07deeb01a70a733d6e943ff86ab91e7f2feba3b2d

Observation 5729fcf9-b6b0-4e6a-a4f9-8a32358e31cc · outbound

This paper cites Neuron-Level Knowledge Attribution in Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Neuron-Level Knowledge Attribution in Large Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.283123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.283123Z digest=sha256:c19f6d7ee82f956d041e5327aaaf26a7ade2a86385c1a798951cf10ecaf8d478

Observation f7e0fd40-5c49-4eb0-b8eb-6d417cdea73a · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace OPT: Open Pre-trained Transformer Language Models

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.376831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.376831Z digest=sha256:5af70e4bf85f6ab94905f20c000ce1c8794fff6d23f48dcba5d558c00e05afbc

Observation f16bf62d-dd4e-4c87-83db-b92a1db5c31e · outbound

This paper cites an unresolved cited work.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-07T15:42:36.146355Z

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.

source=arxiv_source observed=2026-08-07T15:42:34.478018Z digest=sha256:a83e2beab31039eb808acac5c461c368b0f1da28e735c565066ff409104198f0

Observation 011b081c-b633-4b13-b08b-47f08cc71277 · outbound

This paper cites Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.599908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.599908Z digest=sha256:b7ad3e8269e9c8a1a0b649515c133245253bad649f3466bb2379bb64346cfe0e

Observation 02a16147-cfe0-4bce-ad0c-128ffa0dddcf · outbound

This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.703077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.703077Z digest=sha256:0ca1ac3ef1ddc67ab311266d7b15e7d185e5d1655b5353fe47deca7a8fa3f8bf

Observation 28e6be3c-d059-43de-8e0a-485b1903f590 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.774738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.774738Z digest=sha256:c1f5e03ba322df1b5fd433d83c065dd9ae5ed373fcd04668adf3258d1b2c9d91

Observation ce3fa351-96ba-4940-b9f5-f6866efe69fb · outbound

This paper cites online" 'onlinestring :=.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace online" 'onlinestring :=

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.854093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.854093Z digest=sha256:57ac1d824bf087324a56f08b320532e7252b29a319eb5e68ce8cedb16ea63a50

Observation deca8457-878a-47e1-abdf-38d30f342aab · outbound

This paper cites write newline.

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace write newline

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:34.927348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:34.927348Z digest=sha256:84d8eb18f6c218f95d1caef64cf1fb69874f53af5655d1558326f7a71eb5d3d3

Pith citing papers

Observation 423b8540-b259-4a3e-b06f-2504de01f286 · inbound

A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models cites this paper.

A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

Reference 102

Resolution
verified exact
arxiv_id, observed 2026-07-04T19:30:07.679358Z

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.

source=arxiv_source observed=2026-06-25T21:16:36.392606Z digest=sha256:fd060fa875dd099b9cf06896fad4a554c58862d92d2389a8379692494bc05068