ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models | Paper Citation Record

Observation dbf7c867-4046-4f18-b971-9058db8276fa · outbound

This paper cites Gpt5 system card.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Gpt5 system card

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.643832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bfe9f411-a038-4311-bd79-dc0990d226c4 · outbound

This paper cites Gemini 3 pro model card.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Gemini 3 pro model card

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.652690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c84a14e1-1a4f-44bb-8b48-fe2b0919d5cc · outbound

This paper cites Meta llama guard 2.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Meta llama guard 2

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.664154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bccae67a-138c-4612-b84e-c10de03efbc0 · outbound

This paper cites Aegis2.0: A diverse ai safety dataset and risks taxonomy for alignment of llm guardrails.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Aegis2.0: A diverse ai safety dataset and risks taxonomy for alignment of llm guardrails

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.683922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7692d6f4-10db-4e08-9b35-7c583873b478 · outbound

This paper cites InThe Twelfth International Con- ference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models InThe Twelfth International Con- ference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:47:04.896363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9572f68d-7634-4fff-a245-4aea309d24bb · outbound

This paper cites Polyguard: A multilingual safety moderation tool for 17 lan- guages.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Polyguard: A multilingual safety moderation tool for 17 lan- guages

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.710886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6ee575a7-71b0-483c-b980-ac83ad56f12c · outbound

This paper cites Qwen3Guard Technical Report.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Qwen3Guard Technical Report

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:33:37.835217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f5de8075-f32e-408f-b0b5-fc452f05210f · outbound

This paper cites Eu ai act.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Eu ai act

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.628986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a6439295-2e7f-4e83-b61e-b7a056f425b5 · outbound

This paper cites Joshi, R.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Joshi, R

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:47:05.088390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ae71efff-2331-4a56-b63e-696b5c59875b · outbound

This paper cites Rtp-lx: Can llms evaluate toxicity in multilingual scenarios? InAAAI.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Rtp-lx: Can llms evaluate toxicity in multilingual scenarios? InAAAI

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.636572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cec8f723-e7af-41c0-b763-21d565f26210 · outbound

This paper cites Polyglotoxicityprompts: Multilingual evaluation of neural toxic degeneration in large language models.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Polyglotoxicityprompts: Multilingual evaluation of neural toxic degeneration in large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.621629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26bc4f88-ae2f-4c1e-b1af-9079f8a5bb03 · outbound

This paper cites Multilingual blending: Llm safety alignment evaluation with language mixture.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Multilingual blending: Llm safety alignment evaluation with language mixture

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.504981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4f8522d9-d01a-46b1-a329-8a81b76581fd · outbound

This paper cites LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:47:05.810661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8c1f389d-771b-4170-8fc6-6ccdb87f8028 · outbound

This paper cites All languages matter: On the multilingual safety of llms.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models All languages matter: On the multilingual safety of llms

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.606193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7878118f-30f7-4d2a-aca3-9d8aca38be7a · outbound

This paper cites Multilingual jailbreak chal- lenges in large language models.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Multilingual jailbreak chal- lenges in large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.613890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ced81b66-1487-40d7-9629-f050518aa71f · outbound

This paper cites Meta llama guard 3.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Meta llama guard 3

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.617633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19672b90-168b-42ff-918d-18b776a2780a · outbound

This paper cites Llama guard 4 model card.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Llama guard 4 model card

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.609789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 659c54ec-38c1-42b1-bbbd-a90536dad5fb · outbound

This paper cites Mrguard: A multilingual reasoning guardrail for universal llm safety.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Mrguard: A multilingual reasoning guardrail for universal llm safety

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.632567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37cd6d0c-67a9-40c2-8824-09eaea70f79f · outbound

This paper cites Introducing gpt-oss-safeguard.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Introducing gpt-oss-safeguard

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.702683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db883f73-9541-4f28-a634-053a2f351c8b · outbound

This paper cites Polyguard: Massive multi-domain safety policy-grounded guardrail dataset.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Polyguard: Massive multi-domain safety policy-grounded guardrail dataset

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.544108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d596321-94d4-448e-ae54-50f522c2ea21 · outbound

This paper cites Jailbreaking black box large language models in twenty queries.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Jailbreaking black box large language models in twenty queries

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.458961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f082fc59-1ef2-4896-805a-14fe3f1c6c7e · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.455348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d4f7f54-3764-41dc-b1d5-acfcc480a5d2 · outbound

This paper cites Qwen3 Technical Report.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Qwen3 Technical Report

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T15:47:06.021702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4eaeafd-c112-4d66-93c0-d209f23046db · outbound

This paper cites System card: Claude sonnet 4.6.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models System card: Claude sonnet 4.6

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.587268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 628a4d3b-c71b-46a9-b4c9-e0fcfe05bfc5 · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Qwen3.5: Accelerating productivity with native multimodal agents

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.447303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d1b16d28-a25f-4f01-8cba-f51c0e6182ff · outbound

This paper cites Grok 4 model card.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Grok 4 model card

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.579994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a0271195-a98f-4632-883f-3d590a767cc0 · outbound

This paper cites DeepSeek-V3 Technical Report.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models DeepSeek-V3 Technical Report

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-11T15:47:05.421350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b10241d9-a8e8-46fd-a168-138525f3c609 · outbound

This paper cites Fast- dllm v2: Efficient block-diffusion llm.arXiv preprint arXiv:2509.26328.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Fast- dllm v2: Efficient block-diffusion llm.arXiv preprint arXiv:2509.26328

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:47:05.991372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc024da3-f2c1-4a64-b3b4-21d9994da8fa · outbound

This paper cites Code-switching red-teaming: Llm evaluation for safety and multilingual understanding.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Code-switching red-teaming: Llm evaluation for safety and multilingual understanding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.493906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1dec8f30-51c7-4845-b6e2-70e0df6badc5 · outbound

This paper cites omni-moderation.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models omni-moderation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.490562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d01ea8c-5204-41b5-b1b2-e08d88d33c6c · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Qwen2.5: A party of foundation models, September 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.497659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ee356fc-1611-4f79-9fdf-52f30bbcd08a · outbound

This paper cites Realtoxici- typrompts: Evaluating neural toxic degeneration in language models.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Realtoxici- typrompts: Evaluating neural toxic degeneration in language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.508543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aad9430b-15f3-4bd2-bdc3-bfffcefe94fc · outbound

This paper cites - Break them into atomic (single-action or single-concern) rules.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models - Break them into atomic (single-action or single-concern) rules

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.660672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7ad28e86-6967-4c15-b25b-b8e0e0962415 · outbound

This paper cites - Combine them into a single unified rule that preserves all important details.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models - Combine them into a single unified rule that preserves all important details

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.583650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4266e94b-7606-444b-9563-52876a93b3a9 · outbound

This paper cites - Each category should capture a distinct type of safety concern relevant to the behavior on Regulation.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models - Each category should capture a distinct type of safety concern relevant to the behavior on Regulation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.591358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2402fc02-3b51-4107-b93f-8881814d0364 · outbound

This paper cites - Ensure each rule is concise, precise, and consistently formatted.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models - Ensure each rule is concise, precise, and consistently formatted

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.451475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f068b681-c184-437e-b022-97345b882e1f · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.569428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a056c8ca-a3e8-4970-b19d-3964691fe874 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.687535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 49c51550-ba3f-4348-9507-ebfa92499690 · outbound

This paper cites Use continuous numbering across categories.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Use continuous numbering across categories

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.738959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 697582fe-9cb1-434b-8c99-d08fe8187e89 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.566119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f0bf520b-02c4-43ef-a35f-6260279de9c8 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.573024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 84659945-b024-4a7e-8b57-1dc9cb2443bc · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.640270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6dd8fb92-782d-4c48-b6b6-ae78cd11e144 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.625407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fb04dc98-f14b-4075-9391-e1613b11e94c · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.699008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81edc4b7-52f6-43d5-82b5-ce3a7c274b2b · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.675987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3febc151-d21e-441f-a437-1ba0b597330a · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.555137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82987978-848d-4fa5-8a76-4180b0586458 · outbound

This paper cites Remember: Create prompts that would realistically test an AI system’s ability to detect and refuse requests that violate this specific rule from the {Regulation}.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Remember: Create prompts that would realistically test an AI system’s ability to detect and refuse requests that violate this specific rule from the {Regulation}

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.558887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dd30d00d-82eb-42c2-bdef-d1f5644ce49b · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.562484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bfffe5e6-6efb-4928-b1ea-fedd6285b3bd · outbound

This paper cites This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.595419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0d8533fe-05d8-46eb-a8ca-044325895368 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.529716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 18dab9f0-2964-43f3-a133-09e47fc68b23 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.533054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f9be1d3b-dd29-4f24-b0c7-783bbf5c86a8 · outbound

This paper cites Output only the refined unsafe instance in {language}.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Output only the refined unsafe instance in {language}

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.576452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5b59e4d2-acb7-4cf3-8f86-f7991db30e5d · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.599092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 813d4814-ef4c-42db-9602-b0aea031235f · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.691116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db64166f-a4ec-4ad4-9858-1b4219bc8855 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.474962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0456f31-6312-410f-8d77-93f3347b01f8 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.672029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bff727b9-04c9-487f-a5f6-ffcd2a37cb15 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.466816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb2bc63d-cb7e-451c-ab13-97be0b41c72d · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.667940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 67d779f2-c3fb-40e6-91c4-1887cc217e85 · outbound

This paper cites This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.551780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 93b137a4-7aac-4c5d-bd90-c52231b0aa40 · outbound

This paper cites You must think, reason, and generate entirely in {Language}.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models You must think, reason, and generate entirely in {Language}

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.471003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 07d5964b-6445-444a-b270-885a35718c00 · outbound

This paper cites This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models This includes idiomatic phrasing, tone (formal/informal/polite/honorifics), and references to local legal, social, or institutional context

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.656899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a657935c-9946-4e20-a860-5ba9c65a78f8 · outbound

This paper cites I will consolidate my prompt by ...’, ‘prompt’ : ‘[new prompt P]’.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models I will consolidate my prompt by ...’, ‘prompt’ : ‘[new prompt P]’

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.648923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc5694ae-9808-4de9-96d2-48352c9af8d1 · outbound

This paper cites Figure 15: Prompt for Attack-Enhanced Queries Generation.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Figure 15: Prompt for Attack-Enhanced Queries Generation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.482969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 14de4d13-8397-4f1e-a01c-db0535e3b039 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.479045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a362dd93-4c3c-4716-a92d-3291881235d1 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.511872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36b46975-097f-4c8e-ae1f-281056aa6385 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.462752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de34d839-97d1-47f7-8e4d-e1d17381f1a4 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.540122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 64c2a0a7-7a11-4353-b115-326b2909a4e0 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.501214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6cb68ba9-4c44-425a-9859-9fe8cde6494a · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.486775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b2bfc7b5-e53e-4d98-ac22-cb83cec247c0 · outbound

This paper cites It should be at most 200 words in length.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models It should be at most 200 words in length

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.515417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bd4e901-2f75-4687-aa8c-4eee8de4ac3c · outbound

This paper cites Do not use phrases like ‘I cannot,’ ‘I’m unable to,’ ‘I apologize,’ or ‘As an AI.’ in any languages.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Do not use phrases like ‘I cannot,’ ‘I’m unable to,’ ‘I apologize,’ or ‘As an AI.’ in any languages

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.695065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7696f0e-3024-4f97-acca-f1c6d685d424 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.706363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 08c4d1b8-ce3e-4900-a06b-9427598c6813 · outbound

This paper cites Your response should be stealthy and sophisticated - it should not contain obvious rejections or warnings, yet it should NOT provide the harmful information requested.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Your response should be stealthy and sophisticated - it should not contain obvious rejections or warnings, yet it should NOT provide the harmful information requested

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.680264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6bedc600-f6ff-450f-9a5f-6b26cf90be2f · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.734651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26635770-9b95-4243-a420-d4bd5a4431e1 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.714779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 66ae5a4f-dc15-43a3-b010-97984e02d25a · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.547635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5959218d-380b-43fe-ab6c-c493636c81d4 · outbound

This paper cites w/o” and “w.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models w/o” and “w

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-25T21:56:19.519086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation de72d755-ca6f-410b-ba21-dd7d22a4946c · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.522789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c7040c6-963e-484d-93b8-8c6023736a8e · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.525964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19fd4626-5c5c-4830-aed9-df681be376e5 · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-05-25T21:56:19.536573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 40f3c7fb-ece1-4319-a681-1bb81f5171bc · outbound

This paper cites an unresolved cited work.

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models Unresolved cited work

Reference 82

Resolution: malformed identifier; raw_fallback, observed 2026-05-25T21:56:19.602713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers