English
Related papers

Related papers: Understanding Verbatim Memorization in LLMs Throug…

200 papers

Tokenization is the first - and often underappreciated - layer of computation in language models. While Chain-of-Thought (CoT) prompting enables transformer models to approximate recurrent computation by externalizing intermediate steps, we…

Computation and Language · Computer Science 2025-05-21 Xiang Zhang , Juntai Cao , Jiaqi Wei , Yiwei Xu , Chenyu You

When artificial intelligence mistakes memorization for intelligence, it creates a dangerous mirage of reasoning. Existing studies treat memorization and self-knowledge deficits in LLMs as separate issues and do not recognize an intertwining…

Computation and Language · Computer Science 2025-12-23 Sahil Kale

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these…

Epistemic reasoning requires agents to infer the state of the world from partial observations and information about other agents' knowledge. Prior work evaluating LLMs on canonical epistemic puzzles interpreted their behavior through a…

Computation and Language · Computer Science 2026-03-24 Adi Gabay , Gabriel Stanovsky , Liat Peterfreund

Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log loss, leads to implicit meta-learning. The goal of this work…

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

Computation and Language · Computer Science 2023-11-07 Zhenhong Zhou , Jiuyang Xiang , Chaomeng Chen , Sen Su

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Computation and Language · Computer Science 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Machine Learning · Computer Science 2025-10-21 Jing Liu

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. It is often necessary to hypothesize intermediate variables involved in…

Computation and Language · Computer Science 2025-02-13 Michael A. Lepori , Thomas Serre , Ellie Pavlick

Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models such as Ouro perform reasoning by…

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Cryptography and Security · Computer Science 2025-07-29 Xinyue Cui , Johnny Tian-Zheng Wei , Swabha Swayamdipta , Robin Jia

Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better understand how the learning dynamics of LLM finetuning shapes…

Machine Learning · Computer Science 2024-11-19 Katie Kang , Amrith Setlur , Dibya Ghosh , Jacob Steinhardt , Claire Tomlin , Sergey Levine , Aviral Kumar

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Computation and Language · Computer Science 2025-02-25 Moritz Miller , Kumar Shridhar

Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…

Machine Learning · Computer Science 2025-10-14 James R. Golden

Large language models (LLMs) exploit in-context learning (ICL) to solve tasks with only a few demonstrations, but its mechanisms are not yet well-understood. Some works suggest that LLMs only recall already learned concepts from…

Computation and Language · Computer Science 2023-05-18 Jane Pan , Tianyu Gao , Howard Chen , Danqi Chen

Large language models (LLMs) that integrate multiple input roles (e.g., system instructions, user queries, external tool outputs) are increasingly prevalent in practice. Ensuring that the model accurately distinguishes messages from each…

Computation and Language · Computer Science 2025-05-06 Zihao Wang , Yibo Jiang , Jiahao Yu , Heqing Huang

Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense computation. Engram partially decouples retrieval from the backbone, but its token-based keys…

Computation and Language · Computer Science 2026-05-26 Yunao Zheng , Guoyang Xia , Xiaojie Wang , Lei Ren

Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Wojciech Zaremba , Ilya Sutskever

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing graph structures. This task's answer is, in principle,…

Artificial Intelligence · Computer Science 2026-05-12 Katharine Kowalyshyn , Timothy Duggan , Daniel Little , Michael C Hughes
‹ Prev 1 8 9 10 Next ›