Gouki Minegishi

According to our database, Gouki Minegishi authored at least 17 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training.

Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, May, 2026

Steering at the Source: Style Modulation Heads for Robust Persona Control.

Yoshihiro Izawa, Gouki Minegishi, Koshi Eguchi, Sosuke Hosokawa, Kenjiro Taura

CoRR, March, 2026

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment.

Jingyuan Feng, Andrew Gambardella, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, March, 2026

LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation.

Koki Itai, Shunichi Hasegawa, Yuta Yamamoto, Gouki Minegishi, Masaki Otsuki

CoRR, March, 2026

Emergent Analogical Reasoning in Transformers.

Gouki Minegishi, Jingyuan Feng, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, February, 2026

Understanding Emergent Misalignment via Feature Superposition Geometry.

Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs.

Kohsei Matsutani, Shota Takashiro, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, September, 2025

Mechanism of Task-oriented Information Removal in In-context Learning.

Hakaze Cho, Haolin Yang, Gouki Minegishi, Naoya Inoue

CoRR, September, 2025

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties.

Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

CoRR, June, 2025

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks.

Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

Trans. Mach. Learn. Res., 2025

Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models.

Hirohane Takagi, Gouki Minegishi, Shota Kizawa, Issey Sukeda, Hitomi Yanaka

Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence.

Gouki Minegishi, Hiroki Furuta, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words.

Gouki Minegishi, Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials.

Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

Trans. Mach. Learn. Res., 2024

Interpreting Grokked Transformers in Complex Modular Arithmetic.

Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

CoRR, 2024

ADOPT: Modified Adam Can Converge with Any β₂ with the Optimal Rate.

Shohei Taniguchi, Keno Harada, Gouki Minegishi, Yuta Oshima, Seong Cheol Jeong, Go Nagahara, Tomoshi Iiyama, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Grokking Tickets: Lottery Tickets Accelerate Grokking.

Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

CoRR, 2023