English
Related papers

Related papers: Semantic Convergence: Investigating Shared Represe…

200 papers

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

Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…

Computation and Language · Computer Science 2018-07-12 Tomáš Brychcín

Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment remain poorly understood. Following the LiMBeR framework, we…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Constantin Venhoff , Ashkan Khakzar , Sonia Joseph , Philip Torr , Neel Nanda

Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability. We propose SLM -- Sparse Learnable Masks -- a canonical approach for end-to-end…

Machine Learning · Computer Science 2023-04-07 Yihe Dong , Sercan O. Arik

We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages. Beyond word alignment, we…

Computation and Language · Computer Science 2018-04-24 Lifu Huang , Kyunghyun Cho , Boliang Zhang , Heng Ji , Kevin Knight

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Understanding the general priniciples behind transformer models remains a complex endeavor. Experiments with probing and disentangling features using sparse autoencoders (SAE) suggest that these models might manage linear features embedded…

Machine Learning · Computer Science 2024-12-12 Johannes Knittel , Tushaar Gangavarapu , Hendrik Strobelt , Hanspeter Pfister

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the…

Computation and Language · Computer Science 2025-02-03 Daoyang Li , Haiyan Zhao , Qingcheng Zeng , Mengnan Du

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

The use of large language models (LLMs) is expanding rapidly, and open-source versions are becoming available, offering users safer and more adaptable options. These models enable users to protect data privacy by eliminating the need to…

Machine Learning · Computer Science 2024-08-06 Hui Yin , Amir Aryani , Nakul Nambiar

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Computation and Language · Computer Science 2026-02-23 Mathis Le Bail , Jérémie Dentan , Davide Buscaldi , Sonia Vanier

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…

Computation and Language · Computer Science 2026-01-21 Ilia Badanin , Daniil Dzenhaliou , Imanol Schlag

In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Architecture (SA). While Large Language Models (LLMs) demonstrate…

Software Engineering · Computer Science 2026-03-10 Ha Vo , Nhut Tran , Khang Vo , Phat T. Tran-Truong , Son Ha

Multilingual large language models (LLMs) seem to generalize somewhat across languages. We hypothesize this is a result of implicit vector space alignment. Evaluating such alignment, we see that larger models exhibit very high-quality…

Computation and Language · Computer Science 2024-10-03 Qiwei Peng , Anders Søgaard

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

Transformer-based speech language models (SLMs) have significantly improved neural speech recognition and understanding. While existing research has examined how well SLMs encode shallow acoustic and phonetic features, the extent to which…

Computation and Language · Computer Science 2025-09-22 Linyang He , Qiaolin Wang , Xilin Jiang , Nima Mesgarani

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Artificial Intelligence · Computer Science 2025-11-11 Hirohane Takagi , Gouki Minegishi , Shota Kizawa , Issey Sukeda , Hitomi Yanaka