Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:34.927348Z
Paper Citation Record · LEDGER
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.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:34.927348Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-25T21:16:36.392606Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T19:30:07.677913Z
47 of 47 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 1d306a81-6087-4078-b15e-c9bb30816cd2 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Language Models are Few-Shot Learners
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f7ea174d-9138-4304-bff3-45199293e2e5 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0030270b-98e4-4c25-ba40-54e871ad0c6b · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8bc8dc52-34b8-4476-9817-a1d9c6861d66 · outbound
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
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 329266cd-b7eb-4096-baf3-9c10cca7b507 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39c5fca4-d2dc-4489-847d-39654dee5017 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf6c5531-3793-4654-8bf7-6ff5ccaa77cc · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 641ea04d-3d6a-4670-92a9-b9e6ef1cb70b · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Transformer Feed-Forward Layers Are Key-Value Memories
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d18b0f2a-41c8-422e-8a51-3e892a8222cc · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace A Survey on LLM-as-a-Judge
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c46c601-880b-470b-8d8a-55e33dd258a3 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad8fa427-1c89-40f0-a84c-0d01ea855c41 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace LoRA: Low-Rank Adaptation of Large Language Models
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c9e0a81d-3400-4da3-9421-f438f68c5b97 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a47f9934-f65f-439d-95bb-433dd09c4b1e · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace CTRL: A Conditional Transformer Language Model for Controllable Generation
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 51668387-e90c-4c23-9f51-2aa63e824fc6 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be266ba5-146b-4df2-bf88-7669b297273f · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Kummerfeld, and Rada Mihalcea
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5458b9a1-d04a-4b6c-8d6f-a3446b74548a · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 923982c6-6001-4ee4-9417-33db731489ac · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 54f4af7d-478a-4730-a630-eaa271f23cca · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f98c7e8c-78dd-4f6e-a4ea-985c269fd065 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a3cf486-9d7b-4c94-a396-953cb1cb176d · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Pointer Sentinel Mixture Models
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ae10703-9ec0-4440-9443-add8c5e5a0a6 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2873002-6487-4545-88ad-cfda3ac77a59 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 63ed797c-92c4-44b6-b78d-d3a1b93a6163 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c4775586-43ab-4b75-9ed7-cd07cb1fb1b1 · outbound
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
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 f3e95b49-3a12-42ec-8797-3fac0f195282 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c257683-16cb-48fb-a62b-a6baca8c13bb · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Manning, and Chelsea Finn
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3747225d-75ba-47bf-a7c0-81c2fbf4c196 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aafb8c31-4fb1-4b82-9d73-b1ad8801d2ee · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d7a229c4-804a-43cd-ac26-2a4f81e96d8d · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Function Vectors in Large Language Models
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a342c3a4-e89b-4bca-86f7-afb188ca2318 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 30
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 bee9739f-8e95-4919-842f-7b17a6f03b7d · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 572592ee-afe2-490c-9246-afbd008ec68e · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation caf42a89-8f96-4b7a-b82b-b4f12b28c000 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8d5339d-76e1-47eb-8184-3b2997e1852f · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models
Reference 34
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 fa8798e2-dfe8-4a2a-948a-3063f9ce1879 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 81774b8d-8151-4458-9f5b-abf3727b8984 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 63c3cdbe-a1e5-456d-85ec-57ac075670c2 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba919713-722f-441b-acca-c035a371369a · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b50eff71-d362-4bc0-b505-bbc2919538a1 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Knowledge Circuits in Pretrained Transformers
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5729fcf9-b6b0-4e6a-a4f9-8a32358e31cc · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Neuron-Level Knowledge Attribution in Large Language Models
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f7e0fd40-5c49-4eb0-b8eb-6d417cdea73a · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace OPT: Open Pre-trained Transformer Language Models
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f16bf62d-dd4e-4c87-83db-b92a1db5c31e · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Unresolved cited work
Reference 42
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 011b081c-b633-4b13-b08b-47f08cc71277 · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02a16147-cfe0-4bce-ad0c-128ffa0dddcf · outbound
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
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 28e6be3c-d059-43de-8e0a-485b1903f590 · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ce3fa351-96ba-4940-b9f5-f6866efe69fb · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace online" 'onlinestring :=
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation deca8457-878a-47e1-abdf-38d30f342aab · outbound
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace write newline
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 423b8540-b259-4a3e-b06f-2504de01f286 · inbound
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
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.