English
Related papers

Related papers: Sparse Auto-Encoders and Holism about Large Langua…

200 papers

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

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

Large Language Models (LLMs) such as ChatGPT demonstrated the potential to replicate human language abilities through technology, ranging from text generation to engaging in conversations. However, it remains controversial to what extent…

Computation and Language · Computer Science 2025-07-09 Martin Schuele

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Computation and Language · Computer Science 2026-02-26 Pierre Beckmann , Matthieu Queloz

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

Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. However, the enigmatic ``black-box'' nature of LLMs remains a significant challenge for interpretability, hampering…

Computation and Language · Computer Science 2023-12-27 Zhen Tan , Tianlong Chen , Zhenyu Zhang , Huan Liu

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Frame-semantic parsing is a critical task in natural language understanding, yet the ability of large language models (LLMs) to extract frame-semantic arguments remains underexplored. This paper presents a comprehensive evaluation of LLMs…

Computation and Language · Computer Science 2025-02-19 Jacob Devasier , Rishabh Mediratta , Chengkai Li

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

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

This paper explores the ability of large language models to generate and recognize deep cognitive frames, particularly in socio-political contexts. We demonstrate that LLMs are highly fluent in generating texts that evoke specific frames…

Computation and Language · Computer Science 2025-10-07 Hadi Asghari , Sami Nenno

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…

Computation and Language · Computer Science 2026-04-08 Ruikang Zhang , Shuo Wang , Qi Su

Modern Artificial Intelligence applications show great potential for language-related tasks that rely on next-word prediction. The current generation of Large Language Models (LLMs) have been linked to claims about human-like linguistic…

Computation and Language · Computer Science 2024-09-05 Evelina Leivada , Gary Marcus , Fritz Günther , Elliot Murphy

Large Language Models (LLMs) represent a class of deep learning models adept at understanding natural language and generating coherent responses to various prompts or queries. These models far exceed the complexity of conventional neural…

Machine Learning · Computer Science 2024-12-05 Minghao Shao , Abdul Basit , Ramesh Karri , Muhammad Shafique

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

Computation and Language · Computer Science 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

Computation and Language · Computer Science 2026-04-21 Yutong Gao , Qinglin Meng , Yuan Zhou , Liangming Pan

This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights. We utilize an end-to-end system with a speech encoder, which is trained to produce token…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Wonjune Kang , Junteng Jia , Chunyang Wu , Wei Zhou , Egor Lakomkin , Yashesh Gaur , Leda Sari , Suyoun Kim , Ke Li , Jay Mahadeokar , Ozlem Kalinli

Recent advances in Large Language Models (LLMs) have opened new perspectives for automation in optimization. While several studies have explored how LLMs can generate or solve optimization models, far less is understood about what these…

Artificial Intelligence · Computer Science 2025-12-16 Francesca Da Ros , Luca Di Gaspero , Kevin Roitero

Large language models (LLMs) have achieved a milestone that undenia-bly changed many held beliefs in artificial intelligence (AI). However, there remains many limitations of these LLMs when it comes to true language understanding,…

Computation and Language · Computer Science 2023-07-28 Walid S. Saba