Research graph
References from EVA: Editing for Versatile Alignment Against Jailbreaks. Local targets link to admitted publications; unresolved targets remain external evidence.
10.52202/068431-2011
10.52202/068431-2011 · External reference
10.52202/075280-2338
10.52202/075280-2338 · External reference
Universal and transferable adversarial attacks on aligned language models
2023 · External reference
10.18653/v1/2025.findings-acl.1294
10.18653/v1/2025.findings-acl.1294 · External reference
Autodan: Generating stealthy Jailbreak prompts on aligned large language models
External reference
10.1109/satml64287.2025.00010
10.1109/satml64287.2025.00010 · External reference
10.1609/aaai.v39i22.34568
10.1609/aaai.v39i22.34568 · External reference
10.1007/978-3-031-73464-9_11
10.1007/978-3-031-73464-9_11 · External reference
Safety fine-tuning at (almost) no cost: A baseline for vision large language models
External reference
10.1145/3724393
10.1145/3724393 · External reference
LlavaGuard: VLM-based safeguard for vision dataset curation and safety assessment
External reference
10.1007/978-3-031-72661-3_5
10.1007/978-3-031-72661-3_5 · External reference
10.1109/taslpro.2025.3606231
10.1109/taslpro.2025.3606231 · External reference
Fine-tuning aligned language models compromises safety, even when users do not intend to!
External reference
10.63317/2ivv5y3ufu9y
10.63317/2ivv5y3ufu9y · External reference
10.1109/cvpr52733.2024.02325
10.1109/cvpr52733.2024.02325 · External reference
10.52202/079017-4322
10.52202/079017-4322 · External reference
Finding safety neurons in large language models
2024 · External reference
10.18653/v1/2025.acl-long.1233
10.18653/v1/2025.acl-long.1233 · External reference
10.1214/aoms/1177729694
10.1214/aoms/1177729694 · External reference
Mass-editing memory in a transformer
External reference
10.18653/v1/2024.acl-demos.9
10.18653/v1/2024.acl-demos.9 · External reference
DELMAN: Dynamic defense against large language model Jailbreaking with model editing
External reference
10.1609/aaai.v38i19.30150
10.1609/aaai.v38i19.30150 · External reference
10.1007/978-3-031-72992-8_22
10.1007/978-3-031-72992-8_22 · External reference
10.1109/cvpr52688.2022.01042
10.1109/cvpr52688.2022.01042 · External reference
10.52202/079017-1561
10.52202/079017-1561 · External reference
LoRA: Low-rank adaptation of large language models
2022 · External reference
Defending large language models against jailbreak attacks via layer-specific editing
External reference
10.18653/v1/2024.acl-long.568
10.18653/v1/2024.acl-long.568 · External reference
Baseline defenses for adversarial attacks against aligned language models
2023 · External reference
10.52202/079017-1270
10.52202/079017-1270 · External reference
10.18653/v1/2024.acl-long.303
10.18653/v1/2024.acl-long.303 · External reference
10.52202/079017-2651
10.52202/079017-2651 · External reference
10.18653/v1/2024.findings-emnlp.803
10.18653/v1/2024.findings-emnlp.803 · External reference
Fast model editing at scale
External reference
10.18653/v1/2021.emnlp-main.522
10.18653/v1/2021.emnlp-main.522 · External reference
Modifying memories in transformer models
2020 · External reference
10.18653/v1/2022.findings-acl.37
10.18653/v1/2022.findings-acl.37 · External reference
10.52202/068431-1262
10.52202/068431-1262 · External reference
10.18653/v1/2024.acl-long.171
10.18653/v1/2024.acl-long.171 · External reference
10.18653/v1/2025.findings-emnlp.450
10.18653/v1/2025.findings-emnlp.450 · External reference
SafeLLM: Unlearning harmful outputs from large language models against jailbreak attacks
2025 · External reference
10.18653/v1/2025.acl-long.1240
10.18653/v1/2025.acl-long.1240 · External reference
10.52202/075280-0719
10.52202/075280-0719 · External reference
10.48550/arxiv.1706.03762
10.48550/arxiv.1706.03762 · External reference
10.18653/v1/2021.emnlp-main.446
10.18653/v1/2021.emnlp-main.446 · External reference
10.18653/v1/2022.emnlp-main.3
10.18653/v1/2022.emnlp-main.3 · External reference
Glu variants improve transformer
2020 · External reference
GPT-4o system card
2024 · External reference
SparseVLM: Visual token sparsification for efficient vision-language model inference
External reference
10.1109/iccv48922.2021.00045
10.1109/iccv48922.2021.00045 · External reference
10.18653/v1/2023.emnlp-main.20
10.18653/v1/2023.emnlp-main.20 · External reference
10.1007/978-3-030-58452-8_21
10.1007/978-3-030-58452-8_21 · External reference
Wikimedia downloads
2025 · External reference
Harmbench: A standardized evaluation framework for automated red teaming and robust refusal
External reference
10.52202/079017-1745
10.52202/079017-1745 · External reference
Catastrophic Jailbreak of open-source LLMs via exploiting generation
External reference
10.52202/075280-2020
10.52202/075280-2020 · External reference
10.18653/v1/n19-1300
10.18653/v1/n19-1300 · External reference
10.18653/v1/d16-1264
10.18653/v1/d16-1264 · External reference
10.18653/v1/2020.acl-main.130
10.18653/v1/2020.acl-main.130 · External reference
10.3115/1119176.1119195
10.3115/1119176.1119195 · External reference
10.1007/11736790_9
10.1007/11736790_9 · External reference
Training verifiers to solve math word problems
2021 · External reference
10.18653/v1/d13-1170
10.18653/v1/d13-1170 · External reference
10.18653/v1/d19-5409
10.18653/v1/d19-5409 · External reference
Rouge: A package for automatic evaluation of summaries
External reference
MM-Vet v2: A challenging benchmark to evaluate large multimodal models for integrated capabilities
2024 · External reference
10.1109/cvpr52733.2024.00913
10.1109/cvpr52733.2024.00913 · External reference
10.52202/079017-0850
10.52202/079017-0850 · External reference
LLAMA 2: Open foundation and fine-tuned chat models
2023 · External reference
Mistral 7b. arxiv 2023
2024 · External reference
The llama 3 herd of models
2024 · External reference
Qwen2.5 technical report
2024 · External reference
10.52202/075280-1516
10.52202/075280-1516 · External reference
Qwen2. 5-VV technical report
2025 · External reference
InternVL3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency
2025 · External reference
Unresolved reference
2013 · External reference
10.1145/361219.361220
10.1145/361219.361220 · External reference
On adaptive attacks to adversarial example defenses
External reference
10.1016/0169-7439(87)80084-9
10.1016/0169-7439(87)80084-9 · External reference
10.1109/18.61115
10.1109/18.61115 · External reference
