English
Related papers

Related papers: Toward a Flexible Framework for Linear Representat…

200 papers

Interpretability is a key challenge in fostering trust for Large Language Models (LLMs), which stems from the complexity of extracting reasoning from model's parameters. We present the Frame Representation Hypothesis, a theoretically robust…

Computation and Language · Computer Science 2025-11-25 Pedro H. V. Valois , Lincon S. Souza , Erica K. Shimomoto , Kazuhiro Fukui

The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Previous work has shown how to make this notion precise for…

Computation and Language · Computer Science 2025-02-19 Kiho Park , Yo Joong Choe , Yibo Jiang , Victor Veitch

High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circuits to structured semantic directions that align with human-interpretable concepts. While…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Bowei Tian , Xuntao Lyu , Meng Liu , Hongyi Wang , Ang Li

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…

Machine Learning · Computer Science 2025-10-08 Damjan Kalajdzievski

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a…

Computation and Language · Computer Science 2024-04-02 David Chanin , Anthony Hunter , Oana-Maria Camburu

The linear representation hypothesis states that language models (LMs) encode concepts as directions in their latent space, forming organized, multidimensional manifolds. Prior work has largely focused on identifying specific geometries for…

Artificial Intelligence · Computer Science 2026-04-08 Federico Tiblias , Irina Bigoulaeva , Jingcheng Niu , Simone Balloccu , Iryna Gurevych

Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear…

Computation and Language · Computer Science 2026-05-18 Kiho Park , Yo Joong Choe , Victor Veitch

Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple…

Computation and Language · Computer Science 2024-03-07 Yibo Jiang , Goutham Rajendran , Pradeep Ravikumar , Bryon Aragam , Victor Veitch

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…

Machine Learning · Computer Science 2024-12-03 Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Alasdair Newson , Matthieu Cord

We propose the Lattice Representation Hypothesis of large language models: a symbolic backbone that grounds conceptual hierarchies and logical operations in embedding geometry. Our framework unifies the Linear Representation Hypothesis with…

Artificial Intelligence · Computer Science 2026-05-19 Bo Xiong

The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence for this hypothesis would enable researchers to exploit…

Machine Learning · Computer Science 2025-05-22 Michael Lan , Philip Torr , Austin Meek , Ashkan Khakzar , David Krueger , Fazl Barez

Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier. Prior research has shown that a single LLM's concept representations can be captured as steering vectors (SVs), enabling the control of LLM…

Computation and Language · Computer Science 2025-05-21 Youcheng Huang , Chen Huang , Duanyu Feng , Wenqiang Lei , Jiancheng Lv

Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vector representation of the input. However, the mechanism to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Alexandros Doumanoglou , Kurt Driessens , Dimitrios Zarpalas

In this paper, we address the identification problem for the systems characterized by linear time-invariant dynamics with bilinear observation models. More precisely, we consider a suitable parametric description of the system and formulate…

Systems and Control · Electrical Eng. & Systems 2025-02-24 Diyou Liu , Mohammad Khosravi

Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…

Machine Learning · Computer Science 2025-10-14 James R. Golden

Large language models (LLMs) have demonstrated the ability to generate text that realistically reflects a range of different subjective human perspectives. This paper studies how LLMs are seemingly able to reflect more liberal versus more…

Computation and Language · Computer Science 2025-04-03 Junsol Kim , James Evans , Aaron Schein

Recent empirical evidence shows that LLM representations encode human-interpretable concepts. Nevertheless, the mechanisms by which these representations emerge remain largely unexplored. To shed further light on this, we introduce a novel…

Machine Learning · Computer Science 2026-03-03 Yuhang Liu , Dong Gong , Yichao Cai , Erdun Gao , Zhen Zhang , Biwei Huang , Mingming Gong , Anton van den Hengel , Javen Qinfeng Shi

The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics. This study investigates the internal neural representations of cognitive complexity using Bloom's…

Artificial Intelligence · Computer Science 2026-02-20 Bianca Raimondi , Maurizio Gabbrielli

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Despite their success, Large-Language Models (LLMs) still face criticism due to their lack of interpretability. Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insights as they only…

Computation and Language · Computer Science 2025-07-17 Francesco De Santis , Philippe Bich , Gabriele Ciravegna , Pietro Barbiero , Danilo Giordano , Tania Cerquitelli
‹ Prev 1 2 3 10 Next ›