paper
referenced-only
2025
paper:doi-10-18653-v1-2025-naacl-short-33Language models encode numbers using digit representations in base 10
ByAmit Arnold Levy·Mor Geva
Original abstract (expand)
Amit Arnold Levy, Mor Geva. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). 2025.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- Understanding Counting Mechanisms in Large Language and Vision-Language ModelsAmirmohammad Izadi, Fatemeh Askari, Mobin Bagherian, Sadegh Mohammadian, Mohammad Izadi, Mahdieh Soleymani Baghshah Hosein Hasani2026≈ 74%
- ≈ 71%
- Mechanistic Understanding of Language Models in Syntactic Code CompletionDaking Rai, Ziyu Yao Samuel Miller2025≈ 71%
- A Survey of Large Language ModelsKun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie and Ji-Rong Wen Wayne Xin Zhao2026≈ 71%
- Visual Representations inside the Language ModelAmita Kamath, Madeleine Grunde-McLaughlin, Winson Han, Ranjay Krishna Benlin Liu2025≈ 71%
- Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated ProbabilitiesSathvik Nair and Colin Phillips2026≈ 71%
- Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language ModelsPhilip Torr, Fazl Barez Michael Lan2024≈ 71%
- What do Language Models Learn and When? The Implicit Curriculum HypothesisKaiser Sun, Millicent Li, Isabelle Lee, Lindia Tjuatja, Jen-tse Huang, Graham Neubig Emmy Liu2026≈ 71%
- What do Transformers Know about Government?Anisia Katinskaia, Lari Kotilainen, Sathianpong Trangcasanchai, Anh-Duc Vu, Roman Yangarber Jue Hou2024≈ 70%
- Exploring the Role of BERT Token Representations to Explain Sentence Probing ResultsAli Modarressi, Mohammad Taher Pilehvar Hosein Mohebbi2021≈ 70%
- Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language ModelsSeogyeong Jeong, Siddhesh Pawar, Jisu Shin, Jiho Jin, Junho Myung, Alice Oh, Isabelle Augenstein Haeun Yu2026≈ 70%
- Inspecting the concept knowledge graph encoded by modern language modelsMarcelo Mendoza, Alvaro Soto Carlos Aspillaga2021≈ 70%
- Mechanistic Interpretability of Code Correctness in LLMs via Sparse AutoencodersKriz Tahimic and Charibeth Cheng2025≈ 70%
- Learning to Model the World with LanguageYuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan Jessy Lin2024≈ 70%
- Adversarial Representation Engineering: A General Model Editing Framework for Large Language ModelsZeming Wei, Jun Sun, Meng Sun Yihao Zhang2024≈ 70%
- Interpreting Language Model Parametersin corpus2026≈ 69%
- ≈ 68%
- ≈ 68%
- ≈ 65%
- ≈ 65%
- A Mathematical Framework for Transformer Circuitsin corpus2021≈ 63%
- Denotational Design: from meanings to programsin corpus2015≈ 63%
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetsin corpus2023≈ 63%
- Finger Exercises in Formal Concept Analysisin corpus2006≈ 63%
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationsin corpus2023≈ 63%
- ≈ 63%
- Verbalized Eval Awareness Inflates Measured Safetyin corpus2026≈ 63%
- Model Alignment Searchin corpus2025≈ 63%
Similar preprints — Semantic Scholar
Cited by (1)
- 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