Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally?While prior work has focused largely on binary grammatical contrasts, in this work, we study the representation and control of two multidimensional hierarchical grammar phenomena-verb tense and aspect-and for each, identify distinct, orthogonal directions in residual space using linear discriminant analysis.Next, we demonstrate causal control over both grammatical features through concept steering across three generation tasks.Then, we use these identified features in a case study to investigate factors influencing effective steering in multi-token generation.We find that steering strength, location, and duration are crucial parameters for reducing undesirable side effects such as topic shift and degeneration.Our findings suggest that models encode tense and aspect in structurally organized, human-like ways, but effective control of such features during generation is sensitive to multiple factors and requires manual tuning or automated optimization.1

In this paper, we study the surprising impact that truncating text embeddings has on downstream performance.We consistently observe across 6 state-of-the-art text encoders and 26 downstream tasks, that randomly removing up to 50% of embedding dimensions results in only a minor drop in performance, less than 10%, in retrieval and classification tasks.Given the benefits of using smaller-sized embeddings, as well as the potential insights about text encoding, we study this phenomenon and find that, contrary to what is suggested in prior work, this is not the result of an ineffective use of representation space.Instead, we find that a large number of uniformly distributed dimensions actually cause an increase in performance when removed.This would explain why, on average, removing a large number of embedding dimensions results in a marginal drop in performance.We make similar observations when truncating the embeddings used by large language models to make next-token predictions on generative tasks, suggesting that this phenomenon is not isolated to classification or retrieval tasks.Our code is attached to the submission. 1

We propose an anytime bottom-up technique for learning logical rules from large knowledge graphs. We apply the learned rules to predict candidates in the context of knowledge graph completion. Our approach outperforms other rule-based approaches and it is competitive with current state of the art, which is based on latent representations. Besides, our approach is significantly faster, requires less computational resources, and yields an explanation in terms of the rules that propose a candidate.

The linear nearest neighbor (LNN) restriction, present in several current implementations of 1D and 2D quantum circuits, limits the interaction of qubits to those which are adjacent to each other. While there have been several proposals to optimize the process of achieving LNN compliance in 1D circuits, there are few proposals for 2D circuits. Here, we present a new perspective on this problem for 2D quantum circuits. We propose to see this as a multiobjective optimization problem with two objectives: minimizing the size of the 2D grid in the circuit, and minimizing the number of SWAP gates required to achieve LNN compliance. We present some preliminary results which show that these are two contradictory objectives. Since this is common in multiobjective problems, these results indicate that a multiobjective algorithm might be a suitable way to address this problem, since it would make considerations which currently available methods do not make.