English
Related papers

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

200 papers

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

Predicting problem-difficulty in large language models (LLMs) refers to estimating how difficult a task is according to the model itself, typically by training linear probes on its internal representations. In this work, we study the…

Computation and Language · Computer Science 2026-01-21 Stefano Civelli , Pietro Bernardelle , Nicolò Brunello , Gianluca Demartini

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

Computation and Language · Computer Science 2025-03-04 Hongchuan Zeng , Senyu Han , Lu Chen , Kai Yu

This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer layers (space), and varying model sizes (scale). Using…

Computation and Language · Computer Science 2025-05-27 Shashata Sawmya , Micah Adler , Nir Shavit

Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large language models (LLMs) for natural language processing (NLP),…

Machine Learning · Computer Science 2025-11-13 Laura Kopf , Nils Feldhus , Kirill Bykov , Philine Lou Bommer , Anna Hedström , Marina M. -C. Höhne , Oliver Eberle

We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on…

Computation and Language · Computer Science 2025-07-10 Ko-Wei Huang , Yi-Fu Fu , Ching-Yu Tsai , Yu-Chieh Tu , Tzu-Ling Cheng , Cheng-Yu Lin , Yi-Ting Yang , Heng-Yi Liu , Keng-Te Liao , Da-Cheng Juan , Shou-De Lin

Given the remarkable capabilities of large language models (LLMs), there has been a growing interest in evaluating their similarity to the human brain. One approach towards quantifying this similarity is by measuring how well a model…

Computation and Language · Computer Science 2024-06-24 Ebrahim Feghhi , Nima Hadidi , Bryan Song , Idan A. Blank , Jonathan C. Kao

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in…

Computation and Language · Computer Science 2025-07-15 Ameen Ali , Shahar Katz , Lior Wolf , Ivan Titov

Multilingual language models (MLLMs) have demonstrated remarkable abilities to transfer knowledge across languages, despite being trained without explicit cross-lingual supervision. We analyze the parameter spaces of three MLLMs to study…

Computation and Language · Computer Science 2025-06-03 Frederick Riemenschneider , Anette Frank

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

Fine-tuned Large Language Models (LLMs) encode rich task-specific features, but the form of these representations, especially within MLP layers, remains unclear. Empirical inspection of LoRA updates shows that new features concentrate in…

Machine Learning · Computer Science 2025-09-30 Tanya Chowdhury , Atharva Nijasure , Yair Zick , James Allan

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation…

Machine Learning · Computer Science 2025-04-29 Zhenyu Zhang , Zechun Liu , Yuandong Tian , Harshit Khaitan , Zhangyang Wang , Steven Li

While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the…

Computation and Language · Computer Science 2025-01-14 Yongqi Leng , Deyi Xiong

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Computation and Language · Computer Science 2026-04-16 Corentin Kervadec , Iuliia Lysova , Marco Baroni , Gemma Boleda

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial…

Computation and Language · Computer Science 2026-03-30 Jiyuan An , Liner Yang , Mengyan Wang , Luming Lu , Weihua An , Erhong Yang

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

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLMs' behaviours by adjusting their latent…

Computation and Language · Computer Science 2025-01-23 Jingyuan Yang , Rongjun Li , Weixuan Wang , Ziyu Zhou , Zhiyong Feng , Wei Peng

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Computation and Language · Computer Science 2025-10-14 Sunbowen Lee , Qingyu Yin , Chak Tou Leong , Jialiang Zhang , Yicheng Gong , Shiwen Ni , Min Yang , Xiaoyu Shen

Understanding how the brain represents the multifaceted properties of words in context is essential for explaining the neural architecture of human language. Here, we combine large-scale psycholinguistic modeling with naturalistic fMRI to…

Neurons and Cognition · Quantitative Biology 2026-01-21 Xuan Yang , Chuanji Gao , Cheng Xiao , Nicholas Riccardi , Rutvik H. Desai

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Computation and Language · Computer Science 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen