Research graph
References from FiNE: Fine-Grained Neuron-Level Model Editing for Reliable and Safe LLMs. Local targets link to admitted publications; unresolved targets remain external evidence.
GPT-J-6B: A 6 billion parameter autoregressive language model
2021 · External reference
Llama 2: Open foundation and fine-tuned chat models
2023 · External reference
The Llama 3 herd of models
2024 · External reference
Qwen2.5: A party of foundation models
2024 · External reference
Qwen3 technical report
2025 · External reference
10.1109/tnnls.2024.3498935
10.1109/tnnls.2024.3498935 · External reference
10.18653/v1/2023.emnlp-main.632
10.18653/v1/2023.emnlp-main.632 · External reference
10.1145/3698590
10.1145/3698590 · External reference
10.1016/j.ipm.2025.104299
10.1016/j.ipm.2025.104299 · External reference
10.18653/v1/2022.acl-long.581
10.18653/v1/2022.acl-long.581 · External reference
10.52202/068431-1262
10.52202/068431-1262 · External reference
Mass-editing memory in a transformer
2023 · External reference
10.1609/aaai.v38i17.29818
10.1609/aaai.v38i17.29818 · External reference
AlphaEdit: Null-space constrained model editing for language models
2025 · External reference
10.1613/jair.1.17654
10.1613/jair.1.17654 · External reference
A survey of safety on large vision-language models: Attacks, defenses and evaluations
2025 · External reference
Jailbreak attacks and defenses against multimodal generative models: A survey
2024 · External reference
10.18653/v1/2024.acl-long.303
10.18653/v1/2024.acl-long.303 · External reference
10.18653/v1/2024.findings-acl.948
10.18653/v1/2024.findings-acl.948 · External reference
Finding safety neurons in large language models
2026 · External reference
10.18653/v1/2024.acl-long.171
10.18653/v1/2024.acl-long.171 · External reference
Memory-based model editing at scale
2022 · External reference
10.18653/v1/2023.emnlp-main.296
10.18653/v1/2023.emnlp-main.296 · External reference
10.52202/075280-2079
10.52202/075280-2079 · External reference
10.1609/aaai.v38i17.29916
10.1609/aaai.v38i17.29916 · External reference
Editing factual knowledge in language models
2021 · External reference
Fast model editing at scale
2022 · External reference
10.18653/v1/2023.eacl-main.199
10.18653/v1/2023.eacl-main.199 · External reference
10.1016/j.knosys.2023.110826
10.1016/j.knosys.2023.110826 · External reference
10.52202/075280-0774
10.52202/075280-0774 · External reference
10.1145/3627673.3679900
10.1145/3627673.3679900 · External reference
10.18653/v1/2022.emnlp-main.765
10.18653/v1/2022.emnlp-main.765 · External reference
10.1109/iccvw60793.2023.00308
10.1109/iccvw60793.2023.00308 · External reference
A comprehensive study of knowledge editing for large language models
2024 · External reference
10.18653/v1/2024.findings-acl.60
10.18653/v1/2024.findings-acl.60 · External reference
Precise localization of memories: A fine-grained neuron-level knowledge editing technique for LLMs
2025 · External reference
Qwen2.5-VL
2025 · External reference
10.1109/tip.2024.3359045
10.1109/tip.2024.3359045 · External reference
10.1007/s11263-024-02298-y
10.1007/s11263-024-02298-y · External reference
10.48550/arxiv.1706.03762
10.48550/arxiv.1706.03762 · External reference
10.1145/3581783.3612577
10.1145/3581783.3612577 · External reference
10.18653/v1/2024.findings-emnlp.138
10.18653/v1/2024.findings-emnlp.138 · External reference
Safety layers in aligned large language models: The key to LLM security
2025 · External reference
10.18653/v1/p19-1580
10.18653/v1/p19-1580 · External reference
10.18653/v1/w19-4828
10.18653/v1/w19-4828 · External reference
10.1609/aaai.v35i14.17533
10.1609/aaai.v35i14.17533 · 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
10.18653/v1/d18-1179
10.18653/v1/d18-1179 · External reference
10.18653/v1/p19-1459
10.18653/v1/p19-1459 · External reference
Are transformers universal approximators of sequence-to-sequence functions?
2020 · External reference
10.52202/075280-1516
10.52202/075280-1516 · External reference
10.1109/cvpr52733.2024.01239
10.1109/cvpr52733.2024.01239 · External reference
Language models are few-shot learners
2020 · External reference
10.18653/v1/2023.emnlp-main.691
10.18653/v1/2023.emnlp-main.691 · External reference
HarmBench: A standardized evaluation framework for automated red teaming and robust refusal
2024 · External reference
10.52202/079017-1745
10.52202/079017-1745 · External reference
BERTScore: Evaluating text generation with BERT
2020 · External reference
10.18653/v1/d19-1053
10.18653/v1/d19-1053 · External reference
10.18653/v1/2020.acl-main.704
10.18653/v1/2020.acl-main.704 · External reference
Generating informative and diverse conversational responses via adversarial information maximization
2018 · External reference
10.18653/v1/p17-1147
10.18653/v1/p17-1147 · External reference
10.18653/v1/d18-1206
10.18653/v1/d18-1206 · External reference
GPQA: A graduate-level Google-proof Q&A benchmark
2024 · External reference
Evaluating large language models trained on code
2021 · External reference
10.18653/v1/d17-1082
10.18653/v1/d17-1082 · External reference
10.18653/v1/p16-1144
10.18653/v1/p16-1144 · External reference
OpenCompass: A universal evaluation platform for foundation models
2023 · External reference
Im2Text: Describing images using 1 million captioned photographs
2011 · External reference
10.1162/tacl_a_00644
10.1162/tacl_a_00644 · External reference
10.18653/v1/2023.acl-long.546
10.18653/v1/2023.acl-long.546 · External reference
10.18653/v1/k17-1034
10.18653/v1/k17-1034 · External reference
Modifying memories in transformer models
2021 · External reference
