English
Related papers

Related papers: As Language Models Scale, Low-order Linear Depth D…

200 papers

What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…

Computation and Language · Computer Science 2026-02-10 Jasmine Cui , Charles Ye

The rapid growth in natural language processing (NLP) research has led to numerous new models, outpacing our understanding of how they compare to established ones. One major reason for this difficulty is saturating benchmarks, which may not…

Computation and Language · Computer Science 2024-06-18 Ruchit Rawal , Mariya Toneva

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Computation and Language · Computer Science 2021-06-22 Prasanna Parthasarathi , Mohamed Abdelsalam , Joelle Pineau , Sarath Chandar

Surrogate models play a crucial role in retrospectively interpreting complex and powerful black box machine learning models via model distillation. This paper focuses on using model-based trees as surrogate models which partition the…

Machine Learning · Statistics 2023-10-06 Julia Herbinger , Susanne Dandl , Fiona K. Ewald , Sofia Loibl , Giuseppe Casalicchio

We analyze the operation of transformer language adapters, which are small modules trained on top of a frozen language model to adapt its predictions to new target languages. We show that adapted predictions mostly evolve in the source…

Computation and Language · Computer Science 2024-06-11 Jesujoba O. Alabi , Marius Mosbach , Matan Eyal , Dietrich Klakow , Mor Geva

Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesized to facilitate next-token prediction via linear…

Computation and Language · Computer Science 2026-02-02 Eghbal A. Hosseini , Yuxuan Li , Yasaman Bahri , Declan Campbell , Andrew Kyle Lampinen

We conduct a preliminary inquiry into the ability of generative transformer models to deductively reason from premises provided. We observe notable differences in the performance of models coming from different training setups and find that…

Computation and Language · Computer Science 2023-06-05 Peter Belcak , Luca A. Lanzendörfer , Roger Wattenhofer

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…

Computation and Language · Computer Science 2024-07-16 Jérémy Scheurer , Mikita Balesni , Marius Hobbhahn

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models…

Computation and Language · Computer Science 2024-06-11 Zhu Liu , Cunliang Kong , Ying Liu , Maosong Sun

Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…

Computation and Language · Computer Science 2024-12-24 Prateek Verma , Mert Pilanci

Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…

Computation and Language · Computer Science 2024-04-16 Yutaro Yamada , Yihan Bao , Andrew K. Lampinen , Jungo Kasai , Ilker Yildirim

Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…

Computation and Language · Computer Science 2021-12-16 Andrew Wang , Mohit Sudhakar , Yangfeng Ji

Psychological research consistently finds that human ratings of words across diverse semantic scales can be reduced to a low-dimensional form with relatively little information loss. We find that the semantic associations encoded in the…

Computation and Language · Computer Science 2025-08-15 Austin C. Kozlowski , Callin Dai , Andrei Boutyline

Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in…

Machine Learning · Computer Science 2026-01-06 Alex Ning , Vainateya Rangaraju , Yen-Ling Kuo

Transformer-based Large Language Models (LLMs) have become a fixture in modern machine learning. Correspondingly, significant resources are allocated towards research that aims to further advance this technology, typically resulting in…

Machine Learning · Computer Science 2023-12-22 Pratyusha Sharma , Jordan T. Ash , Dipendra Misra

Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formalize this apparent paradox through the first scaling laws for…

Computation and Language · Computer Science 2026-04-16 Dikshant Kukreja , Kshitij Sah , Gautam Gupta , Avinash Anand , Rajiv Ratn Shah , Zhengkui Wang , Aik Beng Ng , Erik Cambria

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…

Computation and Language · Computer Science 2025-03-10 Xuanqing Liu , Luyang Kong , Wei Niu , Afshin Khashei , Belinda Zeng , Steve Johnson , Jon Jay , Davor Golac , Matt Pope

Large-scale neural language models exhibit remarkable performance in in-context learning: the ability to learn and reason about the input context on the fly. This work studies in-context counterfactual reasoning in language models, that is,…

Computation and Language · Computer Science 2025-10-22 Moritz Miller , Bernhard Schölkopf , Siyuan Guo

Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key question is how to quantify the influence of each individual…

Machine Learning · Computer Science 2026-05-12 Zhenshuo Zhang , Minxuan Duan , Hongyang R. Zhang