English
Related papers

Related papers: The Randomness Floor: Measuring Intrinsic Non-Rand…

200 papers

Neural language models are probabilistic models of human text. They are predominantly trained using maximum likelihood estimation (MLE), which is equivalent to minimizing the forward cross-entropy between the empirical data distribution and…

Computation and Language · Computer Science 2024-02-07 Siyu Ren , Zhiyong Wu , Kenny Q. Zhu

We study why continuous diffusion language models (DLMs) have lagged behind discrete diffusion approaches despite their appealing continuous generative dynamics. Under a controlled token--recovery study, we identify token rounding, the…

Computation and Language · Computer Science 2026-03-04 Junzhe Shen , Jieru Zhao , Ziwei He , Zhouhan Lin

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on…

Computation and Language · Computer Science 2026-03-27 Danlu Chen , Ka Sing He , Jiahe Tian , Chenghao Xiao , Zhaofeng Wu , Taylor Berg-Kirkpatrick , Freda Shi

One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…

Computation and Language · Computer Science 2023-04-21 Verena Blaschke , Hinrich Schütze , Barbara Plank

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

Computation and Language · Computer Science 2026-04-01 Zoë Prins , Samuele Punzo , Frank Wildenburg , Giovanni Cinà , Sandro Pezzelle

There is substantial interest in the use of machine learning (ML)-based techniques throughout the electronic computer-aided design (CAD) flow, particularly methods based on deep learning. However, while deep learning methods have achieved…

Machine Learning · Computer Science 2024-03-04 Chester Holtz , Yucheng Wang , Chung-Kuan Cheng , Bill Lin

This work traces the evolution of word-embedding techniques within the natural language processing (NLP) literature. We collect and analyze 149 research articles spanning the period from 1954 to 2025, providing both a comprehensive…

Computers and Society · Computer Science 2026-03-17 Minh Anh Nguyen , Kuheli Sai , Minh Nguyen

Every language in NL has a $k$-head two-way nondeterministic finite automaton (2nfa($k$)) recognizing it. It is known how to build a constant-space verifier algorithm from a 2nfa($k$) for the same language with constant-randomness, but with…

Computational Complexity · Computer Science 2022-06-03 M. Utkan Gezer

Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but driven by statistics rather than grammar. As a result,…

Computation and Language · Computer Science 2025-10-17 Yinxi Li , Yuntian Deng , Pengyu Nie

Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of "emergence" view these capabilities as unlocked at a specific scale, but others attribute…

Machine Learning · Computer Science 2026-02-19 Rosie Zhao , Tian Qin , David Alvarez-Melis , Sham Kakade , Naomi Saphra

Large Language Models (LLMs) have been reported to have strong performance on natural language processing tasks. However, performance metrics such as accuracy do not measure the quality of the model in terms of its ability to robustly…

Machine Learning · Computer Science 2023-06-02 Emanuele La Malfa , Matthew Wicker , Marta Kwiatkowska

We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of…

Computation and Language · Computer Science 2020-06-16 Tim Z. Xiao , Aidan N. Gomez , Yarin Gal

The paper explores how the human natural language structure can be seen as a product of evolution of inter-personal communication code, targeting maximisation of such culture-agnostic and cross-lingual metrics such as anti-entropy,…

Computation and Language · Computer Science 2023-06-13 Anton Kolonin

We present a new method to detect anomalies in texts (in general: in sequences of any data), using language models, in a totally unsupervised manner. The method considers probabilities (likelihoods) generated by a language model, but…

Computation and Language · Computer Science 2024-09-06 Filip Graliński , Ryszard Staruch , Krzysztof Jurkiewicz

Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs,…

Computation and Language · Computer Science 2026-04-23 Deqing Fu , Tianyi Zhou , Mikhail Belkin , Vatsal Sharan , Robin Jia

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate…

Computation and Language · Computer Science 2024-06-13 Angana Borah , Manash Pratim Barman , Amit Awekar

Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always produce identical outputs, even when temperature and other decoding parameters are fixed. In…

Computation and Language · Computer Science 2026-01-29 Claire Nicholson

This paper studies the nonterminal complexity of weakly conditional grammars, and it proves that every recursively enumerable language can be generated by a weak conditional grammar with no more than \textit{seven} nonterminals. Moreover,…

Nuclear Theory · Physics 2014-08-04 Abdurahim Okhunov , Fadhil I. Sharrad , Anwer A. Al-Sammarea

Multilingual LLMs demonstrate strong performance across diverse languages, yet there has been limited systematic analysis of how language information is structured within their internal representation space and how it emerges across layers.…

Computation and Language · Computer Science 2025-11-24 JaeSeong Kim , Suan Lee

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are…

Computation and Language · Computer Science 2020-09-15 Toms Bergmanis , Artūrs Stafanovičs , Mārcis Pinnis