paper
referenced-only
2021
paper:doi-10-18653-v1-2021-acl-long-144Causal analysis of syntactic agreement mechanisms in neural language models
ByMatthew Finlayson·Aaron Mueller·Sebastian Gehrmann·Stuart Shieber·Tal Linzen·Yonatan Belinkov
Original abstract (expand)
Matthew Finlayson, Aaron Mueller, Sebastian Gehrmann, Stuart Shieber, Tal Linzen, Yonatan Belinkov. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Psychologically-Inspired Causal PromptsZhijing Jin, Justus Mattern, Rada Mihalcea, Mrinmaya Sachan, Bernhard Schoelkopf Zhiheng Lyu2023≈ 77%
- Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMsSasha Boguraev and Kyle Mahowald2026≈ 77%
- Evaluating Neural Language Models as Cognitive Models of Language AcquisitionAnnika Lea Heuser, Charles Yang, Jordan Kodner H\'ector Javier V\'azquez Mart\'inez2026≈ 77%
- ≈ 76%
- Convergent Representations of Linguistic Constructions in Human and Artificial Neural SystemsThomas Kinfe, Andreas Maier, Achim Schilling, Patrick Krauss Pegah Ramezani2026≈ 76%
- Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to SemanticsJoshua Lum, Ziyi Liu, Dani Yogatama Isabelle Lee2024≈ 76%
- Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future DirectionsUsman Naseem2026≈ 76%
- The production of meaning in the processing of natural languageQuan Le Thien, Nayan D'Souza, Louis van der Elst Christopher J. Agostino2026≈ 75%
- Mechanistic Interpretability of Brain-to-Speech Models Across Speech ModesAyushi Mishra Maryam Maghsoudi2026≈ 75%
- Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated ProbabilitiesSathvik Nair and Colin Phillips2026≈ 75%
- Neural mechanisms of predictive processing: a collaborative community experiment through the OpenScope programNicholas Audette, Ryszard Auksztulewicz, Krzysztof Basi\'nski, Andr\'e M. Bastos, Michael Berry, Andres Canales-Johnson, Hannah Choi, Claudia Clopath, Uri Cohen, Rui Ponte Costa, Roberto De Filippo, Roman Doronin, S\'everine Durand, Steven P. Errington, Jeffrey P. Gavornik, Colleen J. Gillon, Arno Granier, Jordan P. Hamm, Loreen Hert\"ag, Henry Kennedy, Sandeep Kumar, Alexander Ladd, Hugo Ladret, J\'er\^ome A. Lecoq, Alexander Maier, Patrick McCarthy, Jie Mei, Jorge Mejias, John Hongyu Meng, Fabian Mikulasch, Noga Mudrik, Farzaneh Najafi, Kevin Nejad, Hamed Nejat, Karim Oweiss, Mihai A. Petrovici, Viola Priesemann, Lucas Rudelt, Sarah Ruediger, Simone Russo, Alessandro Salatiello, Walter Senn, Eli Sennesh, Sepehr Sima, Cem Uran, Anna Vasilevskaya, Julien Vezoli, Martin Vinck, Xiao-Jing Wang, Jacob A. Westerberg, Katharina Wilmes, Yihan Sophy Xiong Ido Aizenbud2026≈ 75%
- Combining Causal Models for More Accurate Abstractions of Neural NetworksSara Magliacane, Atticus Geiger Theodora-Mara P\^islar2025≈ 75%
- ≈ 75%
- Multi-Agent Language Models: Advancing Cooperation, Coordination, and AdaptationArjun Vaithilingam Sudhakar2025≈ 74%
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationsin corpus2023≈ 74%
- The Nonverbal Syntax Framework: An Evidence-Based Tiered System for Inferring Learner States from Observable Behavioral CuesMary John, Jaloliddin Rustamov, Zahiriddin Rustamov, Saja Aldabet, Nazar Zaki, Khaled Shuaib Sherzod Turaev2026≈ 74%
- Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in TransformersHenry Conklin, Yukang Yang, Thomas Griffiths, Jonathan Cohen, Sarah-Jane Leslie Andrew Nam2025≈ 74%
- The Same But Different: Structural Similarities and Differences in Multilingual Language ModelingQinan Yu, Matianyu Zang, Carsten Eickhoff, Ellie Pavlick Ruochen Zhang2024≈ 74%
- ≈ 73%
- Model Alignment Searchin corpus2025≈ 73%
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?in corpus2025≈ 72%
- ≈ 72%
- Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiesin corpus2023≈ 71%
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligencein corpus2026≈ 71%
- Why Learning Requires Feelingin corpus2026≈ 70%
- ≈ 70%
Similar preprints — Semantic Scholar
Cited by (3)
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
At sufficient scale, LLMs linearly represent the truth or falsehood of factual statements in their internal activations — a claim supported by PCA visualizations, cross-dataset probe transfer, and cau
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
Distributed alignment search (DAS) resolves two blocking limitations of prior causal abstraction work—brute-force alignment search and the localist assumption that high-level variables map to disjoint
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as