English
Related papers

Related papers: Momentum Point-Perplexity Mechanics in Large Langu…

200 papers

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Machine Learning · Computer Science 2026-02-04 Magamed Taimeskhanov , Samuel Vaiter , Damien Garreau

Token prediction stability remains a challenge in autoregressive generative models, where minor variations in early inference steps often lead to significant semantic drift over extended sequences. A structured modulation mechanism was…

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

When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…

Computation and Language · Computer Science 2025-11-07 Amir Zur , Atticus Geiger , Ekdeep Singh Lubana , Eric Bigelow

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…

Computation and Language · Computer Science 2025-08-11 Stefan Whitaker , Colin Sisate , Marcel Windsor , Nikolai Fairweather , Tarquin Goldborough , Oskar Lindenfeld

Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger. How do language models of different sizes learn during pre-training? Why do larger…

Computation and Language · Computer Science 2023-05-31 Mengzhou Xia , Mikel Artetxe , Chunting Zhou , Xi Victoria Lin , Ramakanth Pasunuru , Danqi Chen , Luke Zettlemoyer , Ves Stoyanov

We conjecture that hidden state vectors corresponding to individual input tokens encode information sufficient to accurately predict several tokens ahead. More concretely, in this paper we ask: Given a hidden (internal) representation of a…

Computation and Language · Computer Science 2024-03-14 Koyena Pal , Jiuding Sun , Andrew Yuan , Byron C. Wallace , David Bau

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Language models can be steered by modifying their internal representations to control concepts such as emotion, style, or truthfulness in generation. However, the conditions for an effective intervention remain unclear and are often…

Machine Learning · Computer Science 2025-08-05 Jianshu She , Xinyue Li , Eric Xing , Zhengzhong Liu , Qirong Ho

A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or…

Machine Learning · Computer Science 2026-02-06 Hanna Mazzawi , Benoit Dherin , Michael Munn , Michael Wunder , Javier Gonzalvo

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Computation and Language · Computer Science 2024-10-17 Andrea Pinto , Tomer Galanti , Randall Balestriero

We tackle the question of whether Large Language Models (LLMs), viewed as dynamical systems with state evolving in the embedding space of symbolic tokens, are observable. That is, whether there exist multiple 'mental' state trajectories…

Artificial Intelligence · Computer Science 2024-05-24 Tian Yu Liu , Stefano Soatto , Matteo Marchi , Pratik Chaudhari , Paulo Tabuada

As language models become more powerful and sophisticated, it is crucial that they remain trustworthy and reliable. There is concerning preliminary evidence that models may attempt to deceive or keep secrets from their operators. To explore…

Machine Learning · Computer Science 2025-05-21 Bartosz Cywiński , Emil Ryd , Senthooran Rajamanoharan , Neel Nanda

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

Computation and Language · Computer Science 2024-08-01 Anqi Zhang , Chaofeng Wu

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

Computation and Language · Computer Science 2026-03-24 Lorenzo Noci , Gregor Bachmann , Seyed-Mohsen Moosavi-Dezfooli , Moin Nabi

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…

Computation and Language · Computer Science 2025-09-16 Alina Klerings , Jannik Brinkmann , Daniel Ruffinelli , Simone Ponzetto
‹ Prev 1 2 3 10 Next ›