Shared results - 2603.16417v1.pdf

2603.16417v1.pdf

Status: Completed

9

Pages

19

Total Citations

0

Verified

0

Hallucinations / Not Found

0

Duplicates

Notes

It is this paper https://arxiv.org/pdf/2603.16417, 

Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive
Preferences, by Quan Cheng

Status	Citation (Found)	Matched Data / Notes	Actions
Hallucination Edited	The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning Liu, Y.; Zeng, Z.; et al. (2025) Advances in Neural Information Processing Systems (NeurIPS)	Raw: [1] Liu, Y., Zeng, Z., et al. (2025). “The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning.” Advances in Neural Information Processing Systems (NeurIPS). arXiv:2506.01347. Match: The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning Authors: Xinyu Zhu; Mengzhou Xia; Zhepei Wei; Wei-Lin Chen; Danqi Chen; Yu Meng Venue: arXiv DOI: 10.48550/arXiv.2506.01347 ISBN: URL: https://arxiv.org/abs/2506.01347 CrossRef arxiv_static matches title/DOI (score: 1.00), but cited author identities disagree with the official list. Unmatched cited author(s): Liu, Y., Zeng, Z.. Official authors: Xinyu Zhu, Mengzhou Xia, Zhepei Wei, Wei-Lin Chen, Danqi Chen, Yu Meng.
Hallucination Edited	Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization Duan, H.; Yi, Y.; Zhang, Z.; Liu, F.; et al. (2024) Findings of EMNLP	Raw: [2] Duan, H., Yi, Y., Zhang, Z., Liu, F., et al. (2024). “Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization.” Findings of EMNLP. arXiv:2403.03419. Match: Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization Authors: Shitong Duan; Xiaoyuan Yi; Peng Zhang; Yan Liu; Zheng Liu; Tun Lu; Xing Xie; Ning Gu Venue: arXiv DOI: 10.48550/arXiv.2403.03419 ISBN: URL: https://arxiv.org/abs/2403.03419 CrossRef arxiv_static matches title/DOI (score: 1.00), but cited author identities disagree with the official list. Unmatched cited author(s): Duan, H., Yi, Y., Zhang, Z., Liu, F.. Official authors: Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu.
Hallucination Edited	How RLHF Amplifies Sycophancy Shapira, N.; Levy, M.; Alavi, S. H.; et al. (2026) arXiv	Raw: [6] Shapira, N., Levy, M., Alavi, S. H., et al. (2026). “How RLHF Amplifies Sycophancy.” arXiv preprint arXiv:2602.01002. Match: How RLHF Amplifies Sycophancy Authors: Itai Shapira; Gerdus Benade; Ariel D. Procaccia Venue: arXiv DOI: 10.48550/arXiv.2602.01002 ISBN: URL: https://arxiv.org/abs/2602.01002 CrossRef arxiv_static matches title/DOI (score: 1.00), but cited author identities disagree with the official list. Unmatched cited author(s): Shapira, N., Levy, M., Alavi, S. H.. Official authors: Itai Shapira, Gerdus Benade, Ariel D. Procaccia.
Minor Error Edited	Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning Zhang, J.; et al. (2024) arXiv	Raw: [3] Zhang, J., et al. (2024). “Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning.” arXiv preprint arXiv:2404.05868. Match: Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning Authors: Ruiqi Zhang; Licong Lin; Yu Bai; Song Mei Venue: arXiv DOI: 10.48550/arXiv.2404.05868 ISBN: URL: https://arxiv.org/abs/2404.05868 CrossRef arxiv_static matches title/DOI (score: 1.00), but cited author identities disagree with the official list. Unmatched cited author(s): Zhang, J.. Official authors: Ruiqi Zhang, Licong Lin, Yu Bai, Song Mei.
Verified Edited	KTO: Model Alignment as Prospect Theoretic Optimization Ethayarajh, K.; Xu, W.; Muennighoff, N.; Jurafsky, D.; and Kiela, D. (2024) Proceedings of ICML	Raw: [4] Ethayarajh, K., Xu, W., Muennighoff, N., Jurafsky, D., and Kiela, D. (2024). “KTO: Model Alignment as Prospect Theoretic Optimization.” Proceedings of ICML. arXiv:2402.01306. Match: KTO: Model Alignment as Prospect Theoretic Optimization Authors: Kawin Ethayarajh; Winnie Xu; Niklas Muennighoff; Dan Jurafsky; Douwe Kiela Venue: arXiv DOI: 10.48550/arXiv.2402.01306 ISBN: URL: https://arxiv.org/abs/2402.01306 Verified via arXiv id 2402.01306.
Verified Edited	Towards Understanding Sycophancy in Language Models Sharma, M.; Tong, M.; Korbak, T.; et al. (2024) Proceedings of ICLR	Raw: [5] Sharma, M., Tong, M., Korbak, T., et al. (2024). “Towards Understanding Sycophancy in Language Models.” Proceedings of ICLR. arXiv:2310.13548. Match: Towards Understanding Sycophancy in Language Models Authors: Mrinank Sharma; Meg Tong; Tomasz Korbak; David Duvenaud; Amanda Askell; Samuel R. Bowman; Newton Cheng; Esin Durmus; Zac Hatfield-Dodds; Scott R. Johnston; Shauna Kravec; Timothy Maxwell; Sam McCandlish; Kamal Ndousse; Oliver Rausch; Nicholas Schiefer; Da Yan; Miranda Zhang; Ethan Perez Venue: arXiv DOI: 10.48550/arXiv.2310.13548 ISBN: URL: https://arxiv.org/abs/2310.13548 Verified via arXiv id 2310.13548.
Verified Edited	Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones Cheng, Q. (2026) arXiv	Raw: [7] Cheng, Q. (2026). “Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones.” arXiv preprint. Match: Why the Valuable Capabilities of LLMs Are Precisely the Unexplainable Ones Authors: Q. Cheng Venue: arXiv:2603.15238 DOI: ISBN: URL: https://arxiv.org/abs/2603.15238 The title, author, and year are consistent with the official arXiv record.
Verified Edited	On the Proper Treatment of Connectionism Smolensky, P. (1988) Behavioral and Brain Sciences	Raw: [8] Smolensky, P. (1988). “On the Proper Treatment of Connectionism.” Behavioral and Brain Sciences, 11(1), 1-23. Match: On the proper treatment of connectionism Authors: Paul Smolensky Venue: Behavioral and Brain Sciences DOI: 10.1017/s0140525x00052432 ISBN: URL: https://doi.org/10.1017/s0140525x00052432 Verified via static CrossRef title search (score: 1.00)
Verified Edited	The Logic of Scientific Discovery Popper, K. R. (1959) Routledge ISBN: 978-0-415-27844-7	Raw: [9] Popper, K. R. (1959). The Logic of Scientific Discovery. Routledge. (Original: Logik der Forschung, 1934.) Match: The Logic of Scientific Discovery Authors: Richard C. Jeffrey; Karl R. Popper Venue: Econometrica DOI: 10.2307/1907578 ISBN: 978-0-415-27844-7 URL: Verified via static CrossRef title search (score: 0.99)
Verified Edited	Antifragile: Things That Gain from Disorder Taleb, N. N. (2012) Random House	Raw: [10] Taleb, N. N. (2012). Antifragile: Things That Gain from Disorder. Random House. Chapter 22: Via Negativa. 8 Match: Antifragile: Things That Gain from Disorder Authors: Nassim Nicholas Taleb Venue: Random House DOI: ISBN: URL: The citation references a specific chapter ('Via Negativa') within the identified book.
Verified Edited	Negative Knowledge: Understanding Professional Learning and Expertise Gartmeier, M.; Bauer, J.; Gruber, H.; and Heid, H. (2008) Vocations and Learning	Raw: [11] Gartmeier, M., Bauer, J., Gruber, H., and Heid, H. (2008). “Negative Knowledge: Understanding Professional Learning and Expertise.” Vocations and Learning, 1(2), 87-103. Match: Negative Knowledge: Understanding Professional Learning and Expertise Authors: Martin Gartmeier; Johannes Bauer; Hans Gruber; Helmut Heid Venue: Vocations and Learning DOI: 10.1007/s12186-008-9006-1 ISBN: URL: https://doi.org/10.1007/s12186-008-9006-1 Verified via static CrossRef title search (score: 1.00)
Verified Edited	Constitutional AI: Harmlessness from AI Feedback Bai, Y.; Kadavath, S.; et al. (2022) arXiv	Raw: [12] Bai, Y., Kadavath, S., et al. (2022). “Constitutional AI: Harmlessness from AI Feedback.” arXiv preprint arXiv:2212.08073. Match: Constitutional AI: Harmlessness from AI Feedback Authors: Yuntao Bai; Saurav Kadavath; Sandipan Kundu; Amanda Askell; Jackson Kernion; Andy Jones; Anna Chen; Anna Goldie; Azalia Mirhoseini; Cameron McKinnon; Carol Chen; Catherine Olsson; Christopher Olah; Danny Hernandez; Dawn Drain; Deep Ganguli; Dustin Li; Eli Tran-Johnson; Ethan Perez; Jamie Kerr; Jared Mueller; Jeffrey Ladish; Joshua Landau; Kamal Ndousse; Kamile Lukosuite; Liane Lovitt; Michael Sellitto; Nelson Elhage; Nicholas Schiefer; Noemi Mercado; Nova DasSarma; Robert Lasenby; Robin Larson; Sam Ringer; Scott Johnston; Shauna Kravec; Sheer El Showk; Stanislav Fort; Tamera Lanham; Timothy Telleen-Lawton; Tom Conerly; Tom Henighan; Tristan Hume; Samuel R. Bowman; Zac Hatfield-Dodds; Ben Mann; Dario Amodei; Nicholas Joseph; Sam McCandlish; Tom Brown; Jared Kaplan Venue: arXiv DOI: 10.48550/arXiv.2212.08073 ISBN: URL: https://arxiv.org/abs/2212.08073 Verified via arXiv id 2212.08073.
Verified Edited	Large Language Model Unlearning Yao, Y.; et al. (2024) Advances in Neural Information Processing Systems (NeurIPS)	Raw: [13] Yao, Y., et al. (2024). “Large Language Model Unlearning.” Advances in Neural Information Processing Systems (NeurIPS). arXiv:2310.10683. Match: Large Language Model Unlearning Authors: Yuanshun Yao; Xiaojun Xu; Yang Liu Venue: Advances in Neural Information Processing Systems 37 DOI: 10.52202/079017-3346 ISBN: URL: https://doi.org/10.52202/079017-3346 Verified via static CrossRef title search (score: 0.99)
Verified Edited	Mind over Machine: The Power of Human Intuition and Expertise in the Era of the Computer Dreyfus, H. L.; and Dreyfus, S. E. (1986) Free Press	Raw: [14] Dreyfus, H. L. and Dreyfus, S. E. (1986). Mind over Machine: The Power of Human Intuition and Expertise in the Era of the Computer. Free Press. Match: Mind over Machine: The Power of Human Intuition and Expertise in the Era of the Computer Authors: Hubert L. Dreyfus; Stuart E. Drey-fus; Lotfi A. Zadeh Venue: IEEE Expert DOI: 10.1109/mex.1987.4307079 ISBN: URL: https://doi.org/10.1109/mex.1987.4307079 Verified via static CrossRef title search (score: 0.99)
Verified Edited	Discovering Language Model Behaviors with Model-Written Evaluations Perez, E.; Ringer, S.; et al. (2023) Findings of ACL	Raw: [15] Perez, E., Ringer, S., et al. (2023). “Discovering Language Model Behaviors with Model-Written Evaluations.” Findings of ACL. arXiv:2212.09251. Match: Discovering Language Model Behaviors with Model-Written Evaluations Authors: Ethan Perez; Sam Ringer; Kamile Lukosiute; Karina Nguyen; Edwin Chen; Scott Heiner; Craig Pettit; Catherine Olsson; Sandipan Kundu; Saurav Kadavath; Andy Jones; Anna Chen; Benjamin Mann; Brian Israel; Bryan Seethor; Cameron McKinnon; Christopher Olah; Da Yan; Daniela Amodei; Dario Amodei; Dawn Drain; Dustin Li; Eli Tran-Johnson; Guro Khundadze; Jackson Kernion; James Landis; Jamie Kerr; Jared Mueller; Jeeyoon Hyun; Joshua Landau; Kamal Ndousse; Landon Goldberg; Liane Lovitt; Martin Lucas; Michael Sellitto; Miranda Zhang; Neerav Kingsland; Nelson Elhage; Nicholas Joseph; Noemi Mercado; Nova DasSarma; Oliver Rausch; Robin Larson; Sam McCandlish; Scott Johnston; Shauna Kravec; Sheer El Showk; Tamera Lanham; Timothy Telleen-Lawton; Tom Brown; Tom Henighan; Tristan Hume; Yuntao Bai; Zac Hatfield-Dodds; Jack Clark; Samuel R. Bowman; Amanda Askell; Roger Grosse; Danny Hernandez; Deep Ganguli; Evan Hubinger; Nicholas Schiefer; Jared Kaplan Venue: Findings of the Association for Computational Linguistics: ACL 2023 DOI: 10.18653/v1/2023.findings-acl.847 ISBN: URL: https://doi.org/10.18653/v1/2023.findings-acl.847 Verified via static CrossRef title search (score: 0.99)
Verified Edited	Simple Synthetic Data Reduces Sycophancy in Large Language Models Wei, J.; et al. (2023) arXiv	Raw: [16] Wei, J., et al. (2023). “Simple Synthetic Data Reduces Sycophancy in Large Language Models.” arXiv preprint arXiv:2308.03958. Match: Simple synthetic data reduces sycophancy in large language models Authors: Jerry Wei; Da Huang; Yifeng Lu; Denny Zhou; Quoc V. Le Venue: arXiv DOI: 10.48550/arXiv.2308.03958 ISBN: URL: https://arxiv.org/abs/2308.03958 Verified via arXiv id 2308.03958.
Verified Edited	BNF: As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss Han, Y.; et al. (2024) OpenReview	Raw: [17] Han, Y., et al. (2024). “BNF: As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss.” OpenReview. Match: BNF: As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss Authors: Venue: DOI: ISBN: URL: The work exists and is typically associated with preprint or conference submission platforms such as OpenReview or ArXiv.
Verified Edited	Negative Knowledge, Expertise and Organisations Parviainen, J.; and Eriksson, M. (2006) International Journal of Management Concepts and Philosophy	Raw: [18] Parviainen, J. and Eriksson, M. (2006). “Negative Knowledge, Expertise and Organisations.” International Journal of Management Concepts and Philosophy, 2(2), 140-153. Match: Negative knowledge, expertise and organisations Authors: Jaana Parviainen; Marja Eriksson Venue: International Journal of Management Concepts and Philosophy DOI: 10.1504/ijmcp.2006.010265 ISBN: URL: https://doi.org/10.1504/ijmcp.2006.010265 Verified via static CrossRef title search (score: 1.00)
Verified Edited	Polanyi’s Revenge and AI’s New Romance with Tacit Knowledge Kambhampati, S. (2021) Communications of the ACM	Raw: [19] Kambhampati, S. (2021). “Polanyi’s Revenge and AI’s New Romance with Tacit Knowledge.” Communications of the ACM, 64(10), 31-33. Match: Polanyi's revenge and AI's new romance with tacit knowledge Authors: Subbarao Kambhampati Venue: Communications of the ACM DOI: 10.1145/3446369 ISBN: URL: https://doi.org/10.1145/3446369 Verified via static CrossRef title search (score: 1.00)