English
Related papers

Related papers: ParaScopes: What do Language Models Activations En…

200 papers

This paper presents a methodology combining multimodal semantic analysis with an eye-tracking experimental protocol to investigate the cognitive effort involved in understanding the communication of future scenarios. To demonstrate the…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Computation and Language · Computer Science 2021-04-15 Nikunj Saunshi , Sadhika Malladi , Sanjeev Arora

Language models have recently been shown capable of performing regression wherein numeric predictions are represented as decoded strings. In this work, we provide theoretical grounds for this capability and furthermore investigate the…

Machine Learning · Computer Science 2025-08-13 Xingyou Song , Dara Bahri

This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their performance on twelve cognitive task categories. Through systematic measurement of…

Computation and Language · Computer Science 2026-05-18 Mahdi Naser-Moghadasi , Faezeh Ghaderi

In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL…

Computation and Language · Computer Science 2025-11-17 Yu Bai , Heyan Huang , Cesare Spinoso-Di Piano , Marc-Antoine Rondeau , Sanxing Chen , Yang Gao , Jackie Chi Kit Cheung

Recently semantic parsing in context has received considerable attention, which is challenging since there are complex contextual phenomena. Previous works verified their proposed methods in limited scenarios, which motivates us to conduct…

Computation and Language · Computer Science 2020-06-16 Qian Liu , Bei Chen , Jiaqi Guo , Jian-Guang Lou , Bin Zhou , Dongmei Zhang

Transformer architectures are the backbone of most modern language models, but understanding the inner workings of these models still largely remains an open problem. One way that research in the past has tackled this problem is by…

Computation and Language · Computer Science 2025-02-04 Utkarsh Tiwari , Aviral Gupta , Michael Hahn

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

Computation and Language · Computer Science 2026-03-03 Yaorui Shi , Yuxin Chen , Siyuan Wang , Sihang Li , Hengxing Cai , Qi Gu , Xiang Wang , An Zhang

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…

Computation and Language · Computer Science 2024-06-11 Lucas Weber , Jaap Jumelet , Elia Bruni , Dieuwke Hupkes

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…

Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model's ability to persist over time can help design models that…

Computation and Language · Computer Science 2022-11-22 Rabab Alkhalifa , Elena Kochkina , Arkaitz Zubiaga

Recently, continuous cache models were proposed as extensions to recurrent neural network language models, to adapt their predictions to local changes in the data distribution. These models only capture the local context, of up to a few…

Machine Learning · Computer Science 2017-11-08 Edouard Grave , Moustapha Cisse , Armand Joulin

This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data, including GPT2, SmolLM2, OpenELM, TinyLlama, Stable LM, and Gemma 2. We…

Computation and Language · Computer Science 2025-02-24 Yen-Che Hsiao , Abhishek Dutta

Most currently deployed large language models (LLMs) undergo continuous training or additional finetuning. By contrast, most research into LLMs' internal mechanisms focuses on models at one snapshot in time (the end of pre-training),…

Machine Learning · Computer Science 2024-11-27 Curt Tigges , Michael Hanna , Qinan Yu , Stella Biderman

While Transformer language models (LMs) are state-of-the-art for information extraction, long text introduces computational challenges requiring suboptimal preprocessing steps or alternative model architectures. Sparse attention LMs can…

Computation and Language · Computer Science 2022-12-01 Joel Stremmel , Brian L. Hill , Jeffrey Hertzberg , Jaime Murillo , Llewelyn Allotey , Eran Halperin

We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…

Computation and Language · Computer Science 2018-04-27 Antonios Anastasopoulos , David Chiang

Large language models (LLMs) now solve multi-step problems by emitting extended chains of thought. During the process, they often re-derive the same intermediate steps across problems, inflating token usage and latency. This saturation of…

Machine Learning · Computer Science 2025-09-17 Aniket Didolkar , Nicolas Ballas , Sanjeev Arora , Anirudh Goyal

The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the…

Computation and Language · Computer Science 2019-04-15 Ravi Shekhar , Ece Takmaz , Raquel Fernández , Raffaella Bernardi

We present a model of speech perception which takes into account effects of correlations between sounds. Words in this model correspond to the attractors of a suitably chosen descent dynamics. The resulting lexicon is rich in short words,…

Statistical Mechanics · Physics 2025-02-28 Jean-Marc Luck , Anita Mehta