paper-with-me

홈 › Papers

Language Models Are Implicitly Continuous

2025-04-04 · Samuele Marro, Davide Evangelista, X. Angelo Huang, Emanuele La Malfa, Michele Lombardi, Michael Wooldridge

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based language models implicitly learn to represent sentences as continuous-time functions defined over a continuous input space. This phenomenon occurs in most state-of-the-art Large Language Models (LLMs), including Llama2, Llama3, Phi3, Gemma, Gemma2, and Mistral, and suggests that LLMs reason about language in ways that fundamentally differ from humans. Our work formally extends Transformers to capture the nuances of time and space continuity in both input and output space. Our results challenge the traditional interpretation of how LLMs understand language, with several linguistic and engineering implications.

📄 PDF Abstract BibTeX arXiv:2504.03933

Code (1)

samuelemarro/continuous-llm-experiments 공식 구현 jax

Tasks

Language Modelling

Similar Papers 제목 키워드 기반

Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel

2021-11-04 · Kevin Eloff, Okko Räsänen, Herman A. Engelbrecht, Arnu Pretorius 외

Multi-agent reinforcement learning has been used as an effective means to study emergent communication between agents, yet little focus has been given to continuous acoustic communication. This would be more akin to huma…

Language AcquisitionMulti-agent Reinforcement LearningQ-Learningreinforcement-learning+1

iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

2024-06-04 · Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei 외

Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. O…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2

Bi-directional Attention with Agreement for Dependency Parsing

2016-08-06 · EMNLP 2016 11 · Hao Cheng, Hao Fang, Xiaodong He, Jianfeng Gao 외

We develop a novel bi-directional attention model for dependency parsing, which learns to agree on headword predictions from the forward and backward parsing directions. The parsing procedure for each direction is formul…

Dependency Parsing

Learning to Caption Images through a Lifetime by Asking Questions

2018-12-01 · Kevin Shen, Amlan Kar, Sanja Fidler

In order to bring artificial agents into our lives, we will need to go beyond supervised learning on closed datasets to having the ability to continuously expand knowledge. Inspired by a student learning in a classroom, …

Active LearningImage Captioning

Learning to Caption Images Through a Lifetime by Asking Questions

2019-10-01 · ICCV 2019 10 · Tingke Shen, Amlan Kar, Sanja Fidler

In order to bring artificial agents into our lives, we will need to go beyond supervised learning on closed datasets to having the ability to continuously expand knowledge. Inspired by a student learning in a classroom, …

Active Learning