Paper Citation Record · LEDGER

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

As of 7 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2606.09701.

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

pith.paper-citation-record.v1
2606.09701 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T16:28:45.017930Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

44 of 44 outbound references displayed

verified exact1
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch8

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bc40a83d-e24f-4c68-ba9d-f55933afd621 · outbound

This paper cites PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-24T02:23:53.717099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bfcb45f3-893a-4583-bdb5-bbb2b273198d · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007187ce-59bf-44bb-aa28-f450c4fe12cd · outbound

This paper cites doi: 10.1038/s41586-025-09422-z.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO doi: 10.1038/s41586-025-09422-z

Reference 3

Resolution: verified exact; doi, observed 2026-06-27T16:31:02.062491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2c5a317f-d912-4688-b608-265afa12644d · outbound

This paper cites 2026 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2026 , eprint=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f0cc40f-96d4-4f99-8282-473948a52bf1 · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06212a62-c280-4935-aa65-c3a475a963d5 · outbound

This paper cites 2023 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2023 , eprint=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1afb594f-26da-4c38-aceb-0b837d0d7dae · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4542dc8-b047-4a5b-9585-5ac5d851617b · outbound

This paper cites an unresolved cited work.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5f48ab-11dc-4c44-8596-bd1f5bd78a61 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Proximal Policy Optimization Algorithms

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.634778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 18e0e604-868a-403d-8f61-bac452f50059 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.639622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 040d9f00-d93b-4005-8405-8c9e808d21d6 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.632119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a60b8832-343f-4735-8be8-2f4d405a5b5e · outbound

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

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.629610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1ae5feb5-f481-4a13-ac88-a3d7afcc6bd9 · outbound

This paper cites an unresolved cited work.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2700a66a-368d-4d69-b561-99ce157d13c5 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics , pages=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics , pages=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3006e1c-116d-4dde-a98f-750032cf7943 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce2a52c5-c8c1-48d7-9857-efd5cfcbdb4b · outbound

This paper cites Great, now write an article about that: The crescendo multi-turn.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Great, now write an article about that: The crescendo multi-turn

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08a03ff-57dd-48a5-aaa4-b3199d638e56 · outbound

This paper cites Red Teaming Language Models with Language Models.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Red Teaming Language Models with Language Models

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.637181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c5ccd1d5-c6a6-425a-b51b-f648313a6152 · outbound

This paper cites 2021 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2021 , eprint=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20a1017-1b0c-4255-a7cb-e3c918f7ac11 · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3eeb44d-a76f-4d09-8b41-fbd0529fe781 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Advances in Neural Information Processing Systems , volume=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e166221-f2a9-4214-a744-7179a86a18cc · outbound

This paper cites 2026 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2026 , eprint=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781265a4-1662-4d4a-aef5-9320da7cc225 · outbound

This paper cites and Singer, Yaron and Karbasi, Amin , journal=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO and Singer, Yaron and Karbasi, Amin , journal=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b99920-c58f-4223-bb95-97db85101993 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T01:27:31.626972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2c843c4-498b-45a6-9034-5a5b46fde3a2 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c05c7bd-1367-4910-ac1b-cd8da3877b31 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0157ab3d-9d3a-4f2c-98f5-a8d0d2f92055 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f9b626-ed2e-4f6e-87e3-a232d10a0bee · outbound

This paper cites Do Anything Now.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Do Anything Now

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 594097f8-ea83-49ad-8aa6-ce56e88c50ee · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7557f243-f665-4019-ac4d-c4ef2edbff8f · outbound

This paper cites 2021 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2021 , eprint=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb99a591-b896-41c6-8f4d-7e4a0172392c · outbound

This paper cites 2022 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2022 , eprint=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eac1b86f-ebb6-4144-b00f-ed6deeadb1d6 · outbound

This paper cites 2023 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2023 , eprint=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c129ae5-d289-42f5-9652-a451efdb158b · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9165e03d-ae0c-4c7e-aebe-41f26d1a5eb9 · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2ac2712-48fe-4547-8c2a-c6944f981680 · outbound

This paper cites 2026 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2026 , eprint=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78e94437-501e-4dc7-81a2-0cc1744643b0 · outbound

This paper cites Arditi, O.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Arditi, O

Reference 35

Resolution: metadata mismatch; doi, observed 2026-06-27T16:31:02.065302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 519b2a57-6f0d-423d-9c47-31e088cbe46e · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6c9f497-62fb-4936-bf4b-625ddbba4891 · outbound

This paper cites Break-Fix.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO Break-Fix

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67f3e782-574a-49b1-9b28-2cbde17a08a6 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed5d607f-37e2-417f-b6ab-8e962bf2a240 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa63efb-b97a-42c0-bcfb-b4169791eb60 · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a08d829d-3b26-42e9-8fb5-ac21b8cb5553 · outbound

This paper cites 2018 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2018 , eprint=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb1d2193-c3d3-439f-a179-7cb377cba55f · outbound

This paper cites 2025 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2025 , eprint=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff5fa8e-c25b-41e7-8602-d0b483c10145 · outbound

This paper cites 2024 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2024 , eprint=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 784b63c2-49b4-4452-b110-fa8c89060b2f · outbound

This paper cites 2026 , eprint=.

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO 2026 , eprint=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-27T16:28:45.017930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.