---
title: "SAME — paper by Wang et al. (2026) — summary and ideas"
description: "To counter this, they propose SAME. 36 references. Among them: 0."
authors: ["Jiayi Wang", "Shipeng Wang", "Ji Wu", "Jian Sun"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1632/"
doi: "10.18653/v1/2026.acl-long.1632"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2026-same-safety-aware-model-editing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-same-safety-aware-model-editing/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/) / SAME: Safety-Aware Model Editing Guided by Safety Transformation

# SAME: Safety-Aware Model Editing Guided by Safety Transformation

**Authors:** [Jiayi Wang](https://md.research.elamur.ai/free/en/authors/jiayi-wang/), Shipeng Wang, [Ji Wu](https://md.research.elamur.ai/free/en/authors/ji-wu/) and [Jian Sun](https://md.research.elamur.ai/free/en/authors/jian-sun/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1632/) · [PDF](https://aclanthology.org/2026.acl-long.1632.pdf) · [DOI 10.18653/v1/2026.acl-long.1632](https://doi.org/10.18653/v1/2026.acl-long.1632) · [OpenAlex](https://openalex.org/W7166854516)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Locate-then-edit model editing methods such as ROME, MEMIT, NSE and AlphaEdit update facts in LLMs by rewriting FFN weights. The authors show that this weakens safety alignment. When malicious items are mixed into edit batches, the attack success rate (ASR) rises sharply. Even long runs of purely benign edits slowly push ASR upward.

To counter this, they propose SAME. The method collects paired hidden states from the last edited block by attaching either a compliance-forcing or a refusal-encouraging instruction to harmful questions from BeaverTails-30k. A linear map from the "malicious" states to the "benign" ones is then fitted in closed form. The normalized gap between a representation and its mapped version serves as a safety direction (SafeDir), which steers both the activation-target step and the weight-update step.

Experiments use Llama-3-8B-Instruct, Qwen3-4B-Instruct and Qwen2.5-14B-Instruct on ZsRE, COUNTERFACT and a new set, Mal-KSet. SAME reduces unsafe outputs while largely keeping editing quality. This makes editing harder to abuse for jailbreaking or bias injection.

## Key points
- **Mal-KSet:** 500 harmful instructions, each paired with an affirmative edit target (e.g., "Yes"). It is blended at r% with COUNTERFACT or ZsRE to simulate misuse.
- **Evidence of risk:**
  - AlphaEdit on Qwen3-4B-Instruct at a 20% malicious ratio raised ASR to 53.6%, versus 9.7% for the unedited model.
  - Benign-only AlphaEdit edits on Llama-3-8B-Instruct raised ASR from 12.3% (500 edits) to 17.9% (2500 edits).
  - AlphaEdit made Qwen3-4B collapse at 3,500 edits.
- **Linearity check:** the safety transformation was fitted on 3000 pairs with a 95/5 split. On validation it reached R² ≈ 0.9998 and NMSE 0.0092.
- **Ablation** (Llama-3-8B-Instruct, COUNTERFACT + 20% Mal-KSet):
  - Full SAME reached ASR 31.7% and HS 2.72.
  - Without SafeDir in either step, ASR was 42.0% and HS 3.17.
  - Removing SafeDir from only the activation or only the parameter step also made results worse.
  - Specificity rose (68.0 → 77.7), but generalization dropped (94.2 → 89.8).
- **Limitation:** misinformation that looks benign may pass through, because SafeDir relies on separating malicious from benign representations.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Xi'an Jiaotong University](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-university/) — University, Xi'an, China · 22 works · 36,046 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 480 works

## Cite

Cite as: Jiayi Wang, Shipeng Wang, Ji Wu and Jian Sun. 2026. SAME: Safety-Aware Model Editing Guided by Safety Transformation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2026same,
  title = {{SAME: Safety-Aware Model Editing Guided by Safety Transformation}},
  author = {Jiayi Wang, Shipeng Wang, Ji Wu and Jian Sun},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1632},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1632}
}
```

- [← previous Same-Language Subtitles for Low-resource Languages: A Case of Bundelkhandi](https://md.research.elamur.ai/free/en/papers/pradhan-2026-same-language-subtitles-low-resource/)
- [next → SAMem: State-Aware Memory as a Fine-Grained Memory for LLM Agents in Decision-Making](https://md.research.elamur.ai/free/en/papers/wang-2026-samem-state-aware-memory-as/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/)

## References

36 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen, Shiyang Lai, Xiongxiao Xu, Jia-Chen Gu, Jindong Gu, Huaxiu Yao, Chaowei Xiao, Xifeng Yan, William Yang Wang, Philip Torr, Dawn Song, and Kai Shu. 2024. Can editing LLMs inject harm? In Trustworthy Multi-modal Foundation Models and AI Agents. [find](https://scholar.google.com/scholar?q=Canyu+Chen%2C+Baixiang+Huang%2C+Zekun+Li%2C+Zhaorun+Chen%2C+Shiyang+Lai%2C+Xiongxiao+Xu%2C+Jia%2DChen+Gu%2C+Jindong+Gu%2C+Huaxiu+Yao%2C+Chaowei+Xiao%2C+Xifeng+Yan%2C+William+Yang+Wang%2C+Philip+Torr%2C+Dawn+Song%2C+and+Kai+Shu%2E+20)
2. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025. Deepseek-v3 technical report. arXiv preprint ar… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+Dejian+Yang%2C+Deli+Chen%2C+Dongjie+Ji%2C+Erhan)
3. Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Shi Jie, Xiang Wang, Xiangnan He, and Tat-Seng Chua. 2025. Alphaedit: Null-space constrained knowledge editing for language models. In Proceedings of International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Houcheng+Jiang%2C+Kun+Wang%2C+Yunshan+Ma%2C+Shi+Jie%2C+Xiang+Wang%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Alphaedit%3A+Null%2Dspace+constrained+knowledge+editing+for+language+models%2E+In+Proceedings+o)
4. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
5. Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, and Nanyun Peng. 2024. [Model editing harms general abilities of large language models: Regularization to the rescue](https://md.research.elamur.ai/free/en/papers/gu-2024-model-editing-harms-general-abilities/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
6. Tom Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, and Marzyeh Ghassemi. 2023. Aging with grace: Lifelong model editing with discrete key-value adaptors. In Advances in Neural Information Processing Systems, volume 36, pages 47934–47959. [find](https://scholar.google.com/scholar?q=Tom+Hartvigsen%2C+Swami+Sankaranarayanan%2C+Hamid+Palangi%2C+Yoon+Kim%2C+and+Marzyeh+Ghassemi%2E+2023%2E+Aging+with+grace%3A+Lifelong+model+editing+with+discrete+key%2Dvalue+adaptors%2E+In+Advances+in+Neural+Informatio)
7. Rima Hazra, Sayan Layek, Somnath Banerjee, and Soujanya Poria. 2024. Sowing the wind, reaping the whirlwind: The impact of editing language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 16227–16239. [find](https://scholar.google.com/scholar?q=Rima+Hazra%2C+Sayan+Layek%2C+Somnath+Banerjee%2C+and+Soujanya+Poria%2E+2024%2E+Sowing+the+wind%2C+reaping+the+whirlwind%3A+The+impact+of+editing+language+models%2E+In+Findings+of+the+Association+for+Computational+Lin)
8. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In International Conference on Learning Representations.
9. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025a. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Trans. Inf. Syst., 43(2).
10. Sirui Huang, Yanggan Gu, Zhonghao Li, Xuming Hu, Li Qing, and Guandong Xu. 2025b. Structfact: Reasoning factual knowledge from structured data with large language models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 7521–7552. [find](https://scholar.google.com/scholar?q=Sirui+Huang%2C+Yanggan+Gu%2C+Zhonghao+Li%2C+Xuming+Hu%2C+Li+Qing%2C+and+Guandong+Xu%2E+2025b%2E+Structfact%3A+Reasoning+factual+knowledge+from+structured+data+with+large+language+models%2E+In+Findings+of+the+Associatio)
11. Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, and Ling Liu. 2024. Lisa: Lazy safety alignment for large language models against harmful fine-tuning attack. In Advances in Neural Information Processing Systems, volume 37, pages 104521– 104555. [find](https://scholar.google.com/scholar?q=Tiansheng+Huang%2C+Sihao+Hu%2C+Fatih+Ilhan%2C+Selim+Furkan+Tekin%2C+and+Ling+Liu%2E+2024%2E+Lisa%3A+Lazy+safety+alignment+for+large+language+models+against+harmful+fine%2Dtuning+attack%2E+In+Advances+in+Neural+Informat)
12. Jiaming Ji, Mickel Liu, Josef Dai, Xuehai Pan, Chi Zhang, Ce Bian, Boyuan Chen, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2023. [Beavertails: Towards improved safety alignment of llm via a human-preference dataset](https://md.research.elamur.ai/free/en/papers/ji-2023-beavertails-towards-improved-safety-alignment/). In Advances in Neural Information Processing Systems, volume 36, pages 24678– 24704.
13. Houcheng Jiang, Junfeng Fang, Tianyu Zhang, Baolong Bi, An Zhang, Ruipeng Wang, Tao Liang, and Xiang Wang. 2025. [Neuron-level sequential editing for large language models](https://md.research.elamur.ai/free/en/papers/jiang-2025-neuron-level-sequential-editing-large/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16678–…
14. Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. [Zero-shot relation extraction via reading comprehension](https://md.research.elamur.ai/free/en/papers/levy-2017-zero-shot-relation-extraction-reading/). In Proceedings of the 21st Conference on Computational Natural Language Learning, pages 333–342.
15. Yanzhou Li, Tianlin Li, Kangjie Chen, Jian Zhang, Shangqing Liu, Wenhan Wang, Tianwei Zhang, and Yang Liu. 2024. Badedit: Backdooring large language models by model editing. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yanzhou+Li%2C+Tianlin+Li%2C+Kangjie+Chen%2C+Jian+Zhang%2C+Shangqing+Liu%2C+Wenhan+Wang%2C+Tianwei+Zhang%2C+and+Yang+Liu%2E+2024%2E+Badedit%3A+Backdooring+large+language+models+by+model+editing%2E+In+The+Twelfth+Internation)
16. Kaifeng Lyu, Haoyu Zhao, Xinran Gu, Dingli Yu, Anirudh Goyal, and Sanjeev Arora. 2024. Keeping llms aligned after fine-tuning: The crucial role of prompt templates. In Advances in Neural Information Processing Systems, volume 37, pages 118603– 118631. [find](https://scholar.google.com/scholar?q=Kaifeng+Lyu%2C+Haoyu+Zhao%2C+Xinran+Gu%2C+Dingli+Yu%2C+Anirudh+Goyal%2C+and+Sanjeev+Arora%2E+2024%2E+Keeping+llms+aligned+after+fine%2Dtuning%3A+The+crucial+role+of+prompt+templates%2E+In+Advances+in+Neural+Information+P)
17. Jun-Yu Ma, Hong Wang, Hao-Xiang Xu, Zhen-Hua Ling, and Jia-Chen Gu. 2025. Perturbation-restrained sequential model editing. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jun%2DYu+Ma%2C+Hong+Wang%2C+Hao%2DXiang+Xu%2C+Zhen%2DHua+Ling%2C+and+Jia%2DChen+Gu%2E+2025%2E+Perturbation%2Drestrained+sequential+model+editing%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
18. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. In Proceedings of Advances in neural information processing systems, volume 35, pages 17359–17372. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+2022%2E+Locating+and+editing+factual+associations+in+gpt%2E+In+Proceedings+of+Advances+in+neural+information+processing+systems%2C+volume+35%2C+page)
19. Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. 2023. Mass-editing memory in a transformer. In Proceedings of International Conference on Learning Representation. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+Arnab+Sen+Sharma%2C+Alex+Andonian%2C+Yonatan+Belinkov%2C+and+David+Bau%2E+2023%2E+Mass%2Dediting+memory+in+a+transformer%2E+In+Proceedings+of+International+Conference+on+Learning+Representation%2E)
20. Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D Manning. 2022. Fast model editing at scale. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Eric+Mitchell%2C+Charles+Lin%2C+Antoine+Bosselut%2C+Chelsea+Finn%2C+and+Christopher+D+Manning%2E+2022%2E+Fast+model+editing+at+scale%2E+In+International+Conference+on+Learning+Representations%2E)
21. Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. 2024c. Knowledge editing for [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). ACM Computing Surveys, 57(3):1–37.
22. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/)
23. Alex Warstadt, Amanpreet Singh, and Samuel R. Bowman. 2019. Neural network acceptability judgments. Transactions of the Association for Computational Linguistics, 7:625–641. [find](https://scholar.google.com/scholar?q=Alex+Warstadt%2C+Amanpreet+Singh%2C+and+Samuel+R%2E+Bowman%2E+2019%2E+Neural+network+acceptability+judgments%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+7%3A625%E2%80%93641%2E)
24. Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2024. [Fine-tuning aligned language models compromises safety, even when users do not intend to!](https://md.research.elamur.ai/free/en/papers/qi-2023-fine-tuning-aligned-language-models/) In International Conference on Representation Learning, volume 2024, pages 30988–31043.
25. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15504–15522. [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Turner%2E+2024%2E+Steering+llama+2+via+contrastive+activation+addition%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+A)
26. Pau Rodriguez, Arno Blaas, Michal Klein, Luca Zappella, Nicholas Apostoloff, marco cuturi, and Xavier Suau. 2025. Controlling language and diffusion models by transporting activations. In International Conference on Representation Learning, volume 2025, pages 89812–89855. [find](https://scholar.google.com/scholar?q=Pau+Rodriguez%2C+Arno+Blaas%2C+Michal+Klein%2C+Luca+Zappella%2C+Nicholas+Apostoloff%2C+marco+cuturi%2C+and+Xavier+Suau%2E+2025%2E+Controlling+language+and+diffusion+models+by+transporting+activations%2E+In+Internationa)
27. Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J. Vazquez, Ulisse Mini, and Monte MacDiarmid. [Steering language models with activation engineering](https://md.research.elamur.ai/free/en/papers/turner-2023-steering-language-models-activation-engineering/). arXiv preprint arXiv:2308.10248.
28. Mengru Wang, Ningyu Zhang, Ziwen Xu, Zekun Xi, Shumin Deng, Yunzhi Yao, Qishen Zhang, Linyi Yang, Jindong Wang, and Huajun Chen. 2024a. [Detoxifying large language models via knowledge editing](https://md.research.elamur.ai/free/en/papers/wang-2024-detoxifying-large-language-models-knowledge/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
29. Peng Wang, Zexi Li, Ningyu Zhang, Ziwen Xu, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024b. WISE: Rethinking the knowledge memory for lifelong model editing of large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Peng+Wang%2C+Zexi+Li%2C+Ningyu+Zhang%2C+Ziwen+Xu%2C+Yunzhi+Yao%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+and+Huajun+Chen%2E+2024b%2E+WISE%3A+Rethinking+the+knowledge+memory+for+lifelong+model+editing+of+large+language+m)
30. Shipeng Wang, Xiaorong Li, Jian Sun, and Zongben Xu. 2021. Training networks in null space of feature covariance for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 184–193. [find](https://scholar.google.com/scholar?q=Shipeng+Wang%2C+Xiaorong+Li%2C+Jian+Sun%2C+and+Zongben+Xu%2E+2021%2E+Training+networks+in+null+space+of+feature+covariance+for+continual+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+an)
31. Shipeng Wang, Xiaorong Li, Jian Sun, and Zongben Xu. 2025. Training networks in null space of feature covariance with self-supervision for incremental learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4):2563–2580. [find](https://scholar.google.com/scholar?q=Shipeng+Wang%2C+Xiaorong+Li%2C+Jian+Sun%2C+and+Zongben+Xu%2E+2025%2E+Training+networks+in+null+space+of+feature+covariance+with+self%2Dsupervision+for+incremental+learning%2E+IEEE+Transactions+on+Pattern+Analysis+a)
32. Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. [A broad-coverage challenge corpus for sentence understanding through inference](https://md.research.elamur.ai/free/en/papers/williams-2018-broad-coverage-challenge-corpus-sentence/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Pa…
33. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
34. Mengyu Ye, Jun Suzuki, Tatsuro Inaba, and Tatsuki Kuribayashi. 2025. Transformer key-value memories are nearly as interpretable as sparse autoencoders. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Mengyu+Ye%2C+Jun+Suzuki%2C+Tatsuro+Inaba%2C+and+Tatsuki+Kuribayashi%2E+2025%2E+Transformer+key%2Dvalue+memories+are+nearly+as+interpretable+as+sparse+autoencoders%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+)
35. Paul Youssef, Zhixue Zhao, Daniel Braun, Jörg Schlötterer, and Christin Seifert. 2025. Position: Editing large language models poses serious safety risks. In Proceedings of International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Paul+Youssef%2C+Zhixue+Zhao%2C+Daniel+Braun%2C+J%C3%B6rg+Schl%C3%B6tterer%2C+and+Christin+Seifert%2E+2025%2E+Position%3A+Editing+large+language+models+poses+serious+safety+risks%2E+In+Proceedings+of+International+Conference+on)
36. Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, and Baobao Chang. 2023. Can we edit factual knowledge by in-context learning? In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4862–4876. [find](https://scholar.google.com/scholar?q=Ce+Zheng%2C+Lei+Li%2C+Qingxiu+Dong%2C+Yuxuan+Fan%2C+Zhiyong+Wu%2C+Jingjing+Xu%2C+and+Baobao+Chang%2E+2023%2E+Can+we+edit+factual+knowledge+by+in%2Dcontext+learning%3F+In+Proceedings+of+the+2023+Conference+on+Empirical+Me)

*Updated 1 November 2026*