Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
Qwen3Guard Technical Report
As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 81 inbound Pith citation observations for arXiv:2510.14276.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T00:43:01.890905Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation a2ee35e7-4f83-48c8-ba17-2020e2e83b0e · inbound
OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference cites this paper.
OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference Qwen3Guard Technical Report
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:39:14.242702Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cf92171-df0c-43c1-af28-a441cfe0d64b · inbound
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking cites this paper.
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking Qwen3Guard Technical Report
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T05:10:16.641500Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1192903c-7a2f-4236-8f6f-d311c236161e · inbound
Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation cites this paper.
Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation Qwen3Guard Technical Report
Reference 23
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-16T06:07:25.534823Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ac3f4e19-64f3-49b7-ba25-df2614565de2 · inbound
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models cites this paper.
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models Qwen3Guard Technical Report
Reference 2025
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-03T01:22:20.614946Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef62d42f-acf5-4d33-a413-8fccf9ef0315 · inbound
Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning cites this paper.
Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning Qwen3Guard Technical Report
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T23:32:42.145394Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 953ff1f0-7746-4841-ad91-8df6107ca5f0 · inbound
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective cites this paper.
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective Qwen3Guard Technical Report
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T21:20:18.557992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d61d6741-9d06-49bb-8e60-f052ea538963 · inbound
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation cites this paper.
FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation Qwen3Guard Technical Report
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T19:00:15.677990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 089d5599-51c5-4e85-863e-53799a233b26 · inbound
Adaptively Robust LLM Monitoring via Activation Watermarking cites this paper.
Adaptively Robust LLM Monitoring via Activation Watermarking Qwen3Guard Technical Report
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T17:39:43.471239Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77548c0f-f68b-4302-b493-eeeabb6d6ba5 · inbound
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models cites this paper.
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models Qwen3Guard Technical Report
Reference 39
- 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 2026-08-07T06:34:17.273281+00:00.
Observation ee9d3177-6c38-429a-a682-9f1fc0279b8e · inbound
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis cites this paper.
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis Qwen3Guard Technical Report
Reference 40
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 0100edde-10da-426a-9a50-ffa15b8d4a14 · inbound
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis cites this paper.
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis Qwen3Guard Technical Report
Reference 40
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T22:03:02.661178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6aae269a-4fcd-4655-b67d-1b764e5a7858 · inbound
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents cites this paper.
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents Qwen3Guard Technical Report
Reference 20
- 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 2026-08-07T06:34:17.273281+00:00.
Observation acb2e677-16d9-4437-bf87-1d765d248428 · inbound
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming cites this paper.
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming Qwen3Guard Technical Report
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T11:43:31.089245Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 895d1e27-5556-4a2e-baa9-e6716d4636dc · inbound
TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense cites this paper.
TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense Qwen3Guard Technical Report
Reference 46
- 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 2026-08-07T06:34:17.273281+00:00.
Observation c1b0cf5e-4bce-459e-90a4-579e2c7709b9 · inbound
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Qwen3Guard Technical Report
Reference 130
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 96198d4b-94d5-4a0a-9e6d-936350d542ae · inbound
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models Qwen3Guard Technical Report
Reference 46
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 5c2330a1-1240-412a-a106-d5c8f896d5c8 · inbound
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models Qwen3Guard Technical Report
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T16:34:08.890416Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 59c4354f-ad08-4875-90f2-886c83a31690 · inbound
Conflicts Make Large Reasoning Models Vulnerable to Attacks cites this paper.
Conflicts Make Large Reasoning Models Vulnerable to Attacks Qwen3Guard Technical Report
Reference 10
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 7a8df8ac-0519-4525-b995-b6cff0ada22a · inbound
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents cites this paper.
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents Qwen3Guard Technical Report
Reference 5
- Resolution
- metadata mismatch
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 9907746f-35e6-4bc4-9247-2c87138b28bf · inbound
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs cites this paper.
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs Qwen3Guard Technical Report
Reference 60
- 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 2026-08-07T06:34:17.273281+00:00.
Observation b97785af-a3bc-40ae-8253-aaa8cc275766 · inbound
TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts cites this paper.
TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts Qwen3Guard Technical Report
Reference 10
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 7f1df501-f39a-4bbc-937e-38143a422378 · inbound
LLM Safety From Within: Detecting Harmful Content with Internal Representations cites this paper.
LLM Safety From Within: Detecting Harmful Content with Internal Representations Qwen3Guard Technical Report
Reference 13
- Resolution
- metadata mismatch
- 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 2026-08-07T06:34:17.273281+00:00.
Observation cbb5fa31-2f11-4671-951b-e95dfa0cdeb3 · inbound
Cross-Lingual Jailbreak Detection via Semantic Codebooks cites this paper.
Cross-Lingual Jailbreak Detection via Semantic Codebooks Qwen3Guard Technical Report
Reference 20
- Resolution
- malformed identifier
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 6ee575a7-71b0-483c-b980-ac83ad56f12c · inbound
ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models cites this paper.
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 2026-08-07T06:34:17.273281+00:00.
Observation 741ebe01-1101-4823-9dcf-8eb789514f8f · inbound
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety cites this paper.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Qwen3Guard Technical Report
Reference 75
- Resolution
- metadata mismatch
- 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 2026-08-07T06:34:17.273281+00:00.
Observation c20d8a6a-bf83-46fb-a9ad-df26c85d8ea5 · inbound
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs cites this paper.
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs Qwen3Guard Technical Report
Reference 80
- 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 2026-08-07T06:34:17.273281+00:00.
Observation a3e94ded-a735-4a6e-bb79-334960950d46 · inbound
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Qwen3Guard Technical Report
Reference 43
- 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 2026-08-07T06:34:17.273281+00:00.
Observation dfe079d6-5def-4232-8c0e-88f2c01d0992 · inbound
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Qwen3Guard Technical Report
Reference 43
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 8bf3d127-5e3c-477e-85fe-4539c4873800 · inbound
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence cites this paper.
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence Qwen3Guard Technical Report
Reference 99
- 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 2026-08-07T06:34:17.273281+00:00.
Observation e2cba8ce-94e2-4df4-b2b4-7ed0663236e0 · inbound
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence cites this paper.
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence Qwen3Guard Technical Report
Reference 99
- 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 2026-08-07T06:34:17.273281+00:00.
Observation a69cbbfd-bae0-439e-81a0-ceffc8106d1d · inbound
GLiGuard: Schema-Conditioned Classification for LLM Safeguard cites this paper.
GLiGuard: Schema-Conditioned Classification for LLM Safeguard Qwen3Guard Technical Report
Reference 12
- Resolution
- metadata mismatch
- 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 2026-08-07T06:34:17.273281+00:00.
Observation a91efb1d-f110-4ee8-98c6-6bce8c59cbdc · inbound
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off cites this paper.
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off Qwen3Guard Technical Report
Reference 24
- Resolution
- metadata mismatch
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 21944711-f9ad-4068-b05e-38b942855f32 · inbound
Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories cites this paper.
Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories Qwen3Guard Technical Report
Reference 25
- 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 2026-08-07T06:34:17.273281+00:00.
Observation f25c482f-3f03-461c-b915-41c5c9b2e414 · inbound
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks cites this paper.
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks Qwen3Guard Technical Report
Reference 47
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 38c12b81-ec92-4a54-9533-a081addca1aa · inbound
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment cites this paper.
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment Qwen3Guard Technical Report
Reference 48
- 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 2026-08-07T06:34:17.273281+00:00.
Observation 6f7cd408-60e2-4749-a641-bda07f119b0b · inbound
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation cites this paper.
PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation Qwen3Guard Technical Report
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T22:33:48.181891Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dc84d407-2b46-47fe-9f78-5f426fb8978c · inbound
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails cites this paper.
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails Qwen3Guard Technical Report
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T23:43:17.768883Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 58d4bf75-186e-4dc1-b5a8-bbb1bd9ba4a0 · inbound
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents cites this paper.
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents Qwen3Guard Technical Report
Reference 50
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T05:51:08.490229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 22cbf2ee-a3bb-487a-9f31-5a3dc50a0cab · inbound
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents cites this paper.
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents Qwen3Guard Technical Report
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T13:28:38.489351Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation addcadd6-44c4-40d7-88bf-852a058f9a43 · inbound
Boundary-targeted Membership Inference Attacks on Safety Classifiers cites this paper.
Boundary-targeted Membership Inference Attacks on Safety Classifiers Qwen3Guard Technical Report
Reference 35
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T08:11:17.564431Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 806d8ec1-9d40-4c23-a64f-9197ae35b049 · inbound
Boundary-targeted Membership Inference Attacks on Safety Classifiers cites this paper.
Boundary-targeted Membership Inference Attacks on Safety Classifiers Qwen3Guard Technical Report
Reference 35
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-25T05:45:24.364866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dfa74ac4-01f4-4a8b-aea0-3baaffb1bc6a · inbound
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue cites this paper.
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue Qwen3Guard Technical Report
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T21:35:04.717507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 102c8e1e-8392-4f15-8e9b-34698f4f9b99 · inbound
HARP: Measuring Harm Amplification in Multi-Agent LLM Systems cites this paper.
HARP: Measuring Harm Amplification in Multi-Agent LLM Systems Qwen3Guard Technical Report
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T17:23:44.848183Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f9c544c2-2970-4610-8795-75b28cedc916 · inbound
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings cites this paper.
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings Qwen3Guard Technical Report
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:03:24.289784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ff6d13ed-0b0c-4314-91bd-5fe17d65b2c0 · inbound
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations cites this paper.
Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations Qwen3Guard Technical Report
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T12:13:26.524287Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 05e3e30e-2f45-44d1-b966-62c353dbe840 · inbound
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models cites this paper.
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models Qwen3Guard Technical Report
Reference 48
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T08:03:13.519898Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a0d915d8-b543-402c-8299-c6941d727df3 · inbound
Triaging Threats to Specialized Guardrails cites this paper.
Triaging Threats to Specialized Guardrails Qwen3Guard Technical Report
Reference 59
- Resolution
- verified exact
- local_arxiv, observed 2026-06-28T22:32:44.290259Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 32818b3e-6f64-4ab0-8415-7e41f8c08743 · inbound
EvoDefense: Co-Evolving Black-Box Defense with Large Language Models cites this paper.
EvoDefense: Co-Evolving Black-Box Defense with Large Language Models Qwen3Guard Technical Report
Reference 5
- Resolution
- malformed identifier
- local_arxiv, observed 2026-07-01T19:56:10.437273Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 34a6731d-7ffc-462b-8994-6888630cd5de · inbound
Learning from Mistakes: Can LLM Self-Recover after Misalignment? cites this paper.
Learning from Mistakes: Can LLM Self-Recover after Misalignment? Qwen3Guard Technical Report
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T18:51:10.298187Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 999dbe27-ee5c-4ed0-bbd7-4c2ac2b91cca · inbound
BraveGuard: From Open-World Threats to Safer Computer-Use Agents cites this paper.
BraveGuard: From Open-World Threats to Safer Computer-Use Agents Qwen3Guard Technical Report
Reference 45
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T21:26:14.200911Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a3361792-4000-4263-9bbe-dc4bf030ba50 · inbound
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models cites this paper.
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models Qwen3Guard Technical Report
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T22:56:20.738256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 87f650aa-4c74-4889-9be3-07c16aecf429 · inbound
Investigating and Alleviating Harm Amplification in LLM Interactions cites this paper.
Investigating and Alleviating Harm Amplification in LLM Interactions Qwen3Guard Technical Report
Reference 36
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T23:16:24.051535Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7ca2c2a7-a9f7-47be-a0a5-efce46f2b391 · inbound
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting cites this paper.
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting Qwen3Guard Technical Report
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T21:16:14.792525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ea4e50c6-120e-4086-bb78-194ac08be0c5 · inbound
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair cites this paper.
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair Qwen3Guard Technical Report
Reference 27
- Resolution
- malformed identifier
- local_arxiv, observed 2026-06-28T10:32:00.153885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 10a7bd08-76f6-408d-888f-9fac76c66858 · inbound
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety cites this paper.
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety Qwen3Guard Technical Report
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T02:16:26.540113Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2e26bcb3-a5f4-4548-aa0a-58d142f7486f · inbound
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs cites this paper.
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs Qwen3Guard Technical Report
Reference 254
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T01:07:30.265011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5677da66-5809-4ddd-96d1-8d009b22d61b · inbound
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs cites this paper.
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs Qwen3Guard Technical Report
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T07:36:45.291932Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 48d2f00c-23e7-478f-84d4-d479a9a27744 · inbound
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance cites this paper.
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance Qwen3Guard Technical Report
Reference 26
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T17:08:43.472292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7866f3d9-92a2-4f16-af08-7305969aeec6 · inbound
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling cites this paper.
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling Qwen3Guard Technical Report
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T03:59:33.713380Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 919a3143-2067-4700-906d-12b4341afadc · 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 Qwen3Guard Technical Report
Reference 132
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T19:30:07.687112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9b5ea55a-911f-4b47-aa53-578cc0a2dbb6 · inbound
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models cites this paper.
PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models Qwen3Guard Technical Report
Reference 44
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-04T19:40:06.686892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a9ec080c-6f31-4bee-85eb-fcd68ae0362a · inbound
RedVox: Safety and Fairness Gaps in Speech Models Across Languages cites this paper.
RedVox: Safety and Fairness Gaps in Speech Models Across Languages Qwen3Guard Technical Report
Reference 178
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T13:59:52.792091Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 840de7ff-2bce-4795-9354-4a3ba6a3be6b · inbound
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety cites this paper.
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety Qwen3Guard Technical Report
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T00:52:55.753869Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 451b577f-e355-4210-91c9-1b1ae3569c9d · inbound
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models cites this paper.
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models Qwen3Guard Technical Report
Reference 43
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T17:35:51.339657Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 18f8e2e8-a9b5-4ac6-943e-d2f0b157d95a · inbound
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing cites this paper.
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing Qwen3Guard Technical Report
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T06:34:18.837556Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5f22d630-37e7-4659-af2c-cde6ae8b2ec9 · inbound
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification cites this paper.
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification Qwen3Guard Technical Report
Reference 46
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T13:48:20.362672Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation eca486b9-8716-48c0-a4c2-d5b3aa0e9e42 · inbound
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety cites this paper.
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety Qwen3Guard Technical Report
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T14:48:32.676927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a08cd464-6fe2-4b80-a965-4cee34df93bc · inbound
SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection cites this paper.
SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection Qwen3Guard Technical Report
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T05:07:18.364787Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33f58612-2cd1-4783-bbab-edb5e84dd497 · inbound
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail cites this paper.
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail Qwen3Guard Technical Report
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T10:04:51.438848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9b7e8732-b495-48ad-bfd8-cb0bf3f02011 · inbound
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment cites this paper.
MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment Qwen3Guard Technical Report
Reference 58
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T07:16:57.009797Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a4eeda0a-0ae7-430e-ac72-7db9b183733a · inbound
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment cites this paper.
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment Qwen3Guard Technical Report
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T10:00:11.484540Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 74607a4b-5e4b-4619-96f8-bb475d4356f1 · inbound
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models cites this paper.
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models Qwen3Guard Technical Report
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T17:07:55.050266Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7aeaac08-ab9b-4bbb-be7c-2051410b33bf · inbound
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs cites this paper.
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs Qwen3Guard Technical Report
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T16:21:27.339175Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 394f09dc-e471-49c1-82ba-a426fa996511 · inbound
Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework cites this paper.
Stateful Guardrails for Multi-Turn LLM Systems: A Conversational Risk Accumulation Framework Qwen3Guard Technical Report
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T12:28:42.789128Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d40fd64-6589-481e-9e53-08b0119ad890 · inbound
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection cites this paper.
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection Qwen3Guard Technical Report
Reference 2015
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T11:40:29.208494Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8dbd1ec-f3d7-4490-9551-643f179de68d · inbound
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety cites this paper.
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety Qwen3Guard Technical Report
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T11:24:49.027826Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ed0c3849-3f89-460d-9de2-e723ffc92b01 · inbound
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions cites this paper.
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Qwen3Guard Technical Report
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T20:11:00.888291Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e2e490ba-21df-4a62-a7d0-872b3bd31cd8 · inbound
One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.
One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Qwen3Guard Technical Report
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T23:07:38.966539Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78c107ad-85f8-49d4-85c9-18d18ad73bde · inbound
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs cites this paper.
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs Qwen3Guard Technical Report
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T16:20:26.886091Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ce19e8a-ced2-4fe2-a713-61ce7b8e48ca · inbound
Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems cites this paper.
Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems Qwen3Guard Technical Report
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T00:43:01.890905Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bc178fed-7253-42ef-866b-51cd6a4120b8 · inbound
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models cites this paper.
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models Qwen3Guard Technical Report
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T23:46:20.553544Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.