English
Related papers

Related papers: Layer by Layer: Uncovering Hidden Representations …

200 papers

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…

Computation and Language · Computer Science 2024-04-26 Zhihao Zhu , Ninglu Shao , Defu Lian , Chenwang Wu , Zheng Liu , Yi Yang , Enhong Chen

The rapid rise of Language Models (LMs) has expanded the capabilities of natural language processing, powering applications from text generation to complex decision-making. While state-of-the-art LMs often boast hundreds of billions of…

Machine Learning · Computer Science 2025-11-24 Maximilian Abstreiter , Sasu Tarkoma , Roberto Morabito

Large language models (LLMs) are typically developed through large-scale pre-training followed by task-specific fine-tuning. Recent advances highlight the importance of an intermediate mid-training stage, where models undergo multiple…

Computation and Language · Computer Science 2025-10-09 Kaixiang Mo , Yuxin Shi , Weiwei Weng , Zhiqiang Zhou , Shuman Liu , Haibo Zhang , Anxiang Zeng

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

Computation and Language · Computer Science 2024-04-17 Haiyan Zhao , Fan Yang , Bo Shen , Himabindu Lakkaraju , Mengnan Du

Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into geometrical relationships between their vector…

Computation and Language · Computer Science 2025-05-26 Raphaël Sarfati , Haley Moller , Toni J. B. Liu , Nicolas Boullé , Christopher Earls

This paper bridges internal and external analysis approaches to large language models (LLMs) by demonstrating that geometric properties of internal model representations serve as reliable proxies for evaluating generated text quality. We…

We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned affine maps trained to predict the next token from intermediate residual streams-as…

Machine Learning · Computer Science 2026-05-12 Gianfranco Lombardo , Giuseppe Trimigno , Stefano Cagnoni

Cross-lingual transfer learning is an important property of multilingual large language models (LLMs). But how do LLMs represent relationships between languages? Every language model has an input layer that maps tokens to vectors. This…

Computation and Language · Computer Science 2023-12-19 Andrea W Wen-Yi , David Mimno

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using…

Machine Learning · Computer Science 2026-05-25 Arnesh Batra , Arush Gumber , Aniket Khandelwal , Jashn Khemani , Anubha Gupta

Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose…

Computation and Language · Computer Science 2024-06-10 Asma Ghandeharioun , Avi Caciularu , Adam Pearce , Lucas Dixon , Mor Geva

Both text-to-image generation and large language models (LLMs) have made significant advancements. However, many text-to-image models still employ the somewhat outdated T5 and CLIP as their text encoders. In this work, we investigate the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Andrew Z. Wang , Songwei Ge , Tero Karras , Ming-Yu Liu , Yogesh Balaji

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Computation and Language · Computer Science 2024-10-21 Thennal D K , Tim Fischer , Chris Biemann

Large transformers are powerful architectures used for self-supervised data analysis across various data types, including protein sequences, images, and text. In these models, the semantic structure of the dataset emerges from a sequence of…

Machine Learning · Computer Science 2023-10-31 Lucrezia Valeriani , Diego Doimo , Francesca Cuturello , Alessandro Laio , Alessio Ansuini , Alberto Cazzaniga

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

We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models. It uses clustering to discover the encoded concepts and explains them by aligning with a large…

Computation and Language · Computer Science 2022-06-28 Hassan Sajjad , Nadir Durrani , Fahim Dalvi , Firoj Alam , Abdul Rafae Khan , Jia Xu

End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…

Computation and Language · Computer Science 2021-05-04 Siddharth Dalmia , Brian Yan , Vikas Raunak , Florian Metze , Shinji Watanabe

The standard in LLM-based prediction is to use the final-layer representation as the input to a downstream predictor. However, intermediate layers may encode complementary task-relevant signals. Existing approaches therefore either search…

Computation and Language · Computer Science 2026-05-14 Tom Ulanovski , Eyal Blyachman , Maya Bechler-Speicher

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of…

Computation and Language · Computer Science 2025-05-16 Houjing Wei , Yuting Shi , Naoya Inoue

Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift…

Computation and Language · Computer Science 2025-07-28 Chongyang Tao , Tao Shen , Shen Gao , Junshuo Zhang , Zhen Li , Kai Hua , Wenpeng Hu , Zhengwei Tao , Shuai Ma