English
Related papers

Related papers: Interpreting Language Models Through Concept Descr…

200 papers

This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations. Although metaphor processing has gained significant…

Computation and Language · Computer Science 2025-07-22 Elisa Sanchez-Bayona , Rodrigo Agerri

Large Language Models have demonstrated remarkable capabilities in natural language processing, yet their decision-making processes often lack transparency. This opaqueness raises significant concerns regarding trust, bias, and model…

With the continue development of Convolutional Neural Networks (CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as model interpretation. While…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Hamed Behzadi-Khormouji , José Oramas

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

Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by…

Computation and Language · Computer Science 2025-07-01 Ala N. Tak , Amin Banayeeanzade , Anahita Bolourani , Mina Kian , Robin Jia , Jonathan Gratch

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…

Machine Learning · Computer Science 2026-03-10 Antonio De Santis , Schrasing Tong , Marco Brambilla , Lalana Kagal

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

Reasoning is a fundamental aspect of human intelligence that plays a crucial role in activities such as problem solving, decision making, and critical thinking. In recent years, large language models (LLMs) have made significant progress in…

Computation and Language · Computer Science 2023-05-29 Jie Huang , Kevin Chen-Chuan Chang

In recent years, large language models (LLMs) have made significant advancements in developing human-like and engaging dialogue systems. However, in tasks such as consensus-building and persuasion, LLMs often struggle to resolve conflicts…

Artificial Intelligence · Computer Science 2025-11-14 Zhaoqun Li , Xiaotong Fang , Chen Chen , Mengze Li , Beishui Liao

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Machine Learning · Computer Science 2025-03-17 Theodora-Mara Pîslar , Sara Magliacane , Atticus Geiger

In this paper, an approach for concept extraction from documents using pre-trained large language models (LLMs) is presented. Compared with conventional methods that extract keyphrases summarizing the important information discussed in a…

Computation and Language · Computer Science 2025-04-23 Ebrahim Norouzi , Sven Hertling , Harald Sack

Advancements in natural language generation (NLG) and large language models (LLMs) have led to proficient text generation in various tasks. However, integrating intricate constraints into neural text generation, due to LLMs' opacity,…

Computation and Language · Computer Science 2024-03-22 Xiang Chen , Xiaojun Wan

Automated algorithm design is entering a new phase: Large Language Models can now generate full optimisation (meta)heuristics, explore vast design spaces and adapt through iterative feedback. Yet this rapid progress is largely…

Artificial Intelligence · Computer Science 2025-11-21 Niki van Stein , Anna V. Kononova , Thomas Bäck

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

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…

Artificial Intelligence · Computer Science 2025-10-14 Daking Rai , Yilun Zhou , Shi Feng , Abulhair Saparov , Ziyu Yao

Large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks. Understanding how LLMs internally represent knowledge remains a significant challenge. Despite Sparse Autoencoders (SAEs) have…

Computation and Language · Computer Science 2025-09-26 Haoxuan Li , Zhen Wen , Qiqi Jiang , Chenxiao Li , Yuwei Wu , Yuchen Yang , Yiyao Wang , Xiuqi Huang , Minfeng Zhu , Wei Chen

Being able to interpret, or explain, the predictions made by a machine learning model is of fundamental importance. This is especially true when there is interest in deploying data-driven models to make high-stakes decisions, e.g. in…

Machine Learning · Computer Science 2019-10-01 An-phi Nguyen , María Rodríguez Martínez

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Computation and Language · Computer Science 2025-11-05 Masha Fedzechkina , Eleonora Gualdoni , Sinead Williamson , Katherine Metcalf , Skyler Seto , Barry-John Theobald

The rise of large language models (LLMs) has significantly impacted various domains, including natural language processing (NLP) and image generation, by making complex computational tasks more accessible. While LLMs demonstrate impressive…

Databases · Computer Science 2024-10-15 Ananya Rahaman , Anny Zheng , Mostafa Milani , Fei Chiang , Rachel Pottinger

Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well?…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Mu Cai , Zeyi Huang , Yuheng Li , Utkarsh Ojha , Haohan Wang , Yong Jae Lee