English
Related papers

Related papers: Finding Neurons in a Haystack: Case Studies with S…

200 papers

Recent studies suggest that the deeper layers of Large Language Models (LLMs) contribute little to representation learning and can often be removed without significant performance loss. However, such claims are typically drawn from narrow…

Artificial Intelligence · Computer Science 2026-01-28 Xinyuan Song , Keyu Wang , PengXiang Li , Lu Yin , Shiwei Liu

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In…

Computation and Language · Computer Science 2025-05-26 Jannik Brinkmann , Chris Wendler , Christian Bartelt , Aaron Mueller

Understanding whether large language models (LLMs) capture structured meaning requires examining how they represent concept relationships. In this work, we study three models of increasing scale: Pythia-70M, GPT-2, and Llama 3.1 8B,…

Computation and Language · Computer Science 2026-04-01 Andor Diera , Ansgar Scherp

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised…

Computation and Language · Computer Science 2025-12-03 Marco Bronzini , Carlo Nicolini , Bruno Lepri , Jacopo Staiano , Andrea Passerini

Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any…

Machine Learning · Computer Science 2024-05-31 Zhenmei Shi , Junyi Wei , Zhuoyan Xu , Yingyu Liang

In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. However, these methods typically only focus on explaining the very…

Machine Learning · Computer Science 2024-05-14 Tuomas Oikarinen , Tsui-Wei Weng

Large language models (LLMs) have complicated internal dynamics, but induce representations of words and phrases whose geometry we can study. Human language processing is also opaque, but neural response measurements can provide (noisy)…

Computation and Language · Computer Science 2023-11-01 Jiaang Li , Antonia Karamolegkou , Yova Kementchedjhieva , Mostafa Abdou , Sune Lehmann , Anders Søgaard

Large-language models (LLMs) have been shown to respond in a variety of ways for classification tasks outside of question-answering. LLM responses are sometimes called "hallucinations" since the output is not what is ex pected. Memorization…

Computation and Language · Computer Science 2025-12-16 John E. Ortega , Dhruv D. Joshi , Matt P. Borkowski

As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble…

Computation and Language · Computer Science 2025-06-12 Yuxin Chen , Yiran Zhao , Yang Zhang , An Zhang , Kenji Kawaguchi , Shafiq Joty , Junnan Li , Tat-Seng Chua , Michael Qizhe Shieh , Wenxuan Zhang

This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. By activation map we refer to the intermediate output of the multi-layer perceptrons (MLPs) after a…

Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated excellent multilingual capabilities, which can express the…

Computation and Language · Computer Science 2024-11-27 Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

With the rise of Large Language Models (LLMs), the novel metric "Brainscore" emerged as a means to evaluate the functional similarity between LLMs and human brain/neural systems. Our efforts were dedicated to mining the meaning of the novel…

Neurons and Cognition · Quantitative Biology 2024-05-16 Jingkai Li

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Thomas Norrenbrock , Marco Rudolph , Bodo Rosenhahn

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Computation and Language · Computer Science 2025-02-25 Moritz Miller , Kumar Shridhar

Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, yet little is known about how emotion recognition is internally represented. In this work, we investigate the internal mechanisms of emotion…

Computation and Language · Computer Science 2026-04-29 Bangzhao Shu , Arinjay Singh , Mai ElSherief

Probing strategies have been shown to detect the presence of various linguistic features in large language models; in particular, semantic features intermediate to the "natural logic" fragment of the Natural Language Inference task (NLI).…

Computation and Language · Computer Science 2023-04-21 Julia Rozanova , Marco Valentino , Lucas Cordeiro , Andre Freitas

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive…

Deep Learning (DL) , a variant of the neural network algorithms originally proposed in the 1980s, has made surprising progress in Artificial Intelligence (AI), ranging from language translation, protein folding, autonomous cars, and more…

Artificial Intelligence · Computer Science 2023-07-24 Stephen Josè Hanson , Vivek Yadav , Catherine Hanson