English
Related papers

Related papers: LLM Interpretability with Identifiable Temporal-In…

200 papers

This study introduces a groundbreaking approach to simultaneous interpretation by directly leveraging the predictive capabilities of Large Language Models (LLMs). We present a novel algorithm that generates real-time translations by…

Computation and Language · Computer Science 2024-07-22 Kurando Iida , Kenjiro Mimura , Nobuo Ito

Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifying the best-performing LLM for a given task is a significant…

Computation and Language · Computer Science 2025-11-13 Idan Kashani , Avi Mendelson , Yaniv Nemcovsky

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

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Machine Learning · Computer Science 2026-02-09 John Yan , Michael Yu , Yuqi Sun , Alexander Duffy , Tyler Marques , Matthew Lyle Olson

Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…

Computation and Language · Computer Science 2024-04-16 Yutaro Yamada , Yihan Bao , Andrew K. Lampinen , Jungo Kasai , Ilker Yildirim

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

Large Language Models (LLMs) are increasingly being used in education, yet their correctness alone does not capture the quality, reliability, or pedagogical validity of their problem-solving behavior, especially in mathematics, where…

Computers and Society · Computer Science 2025-10-22 Sagnik Dakshit , Sushmita Sinha Roy

In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and enriching datasets with interpretable labels. Traditional…

Computation and Language · Computer Science 2025-11-12 Mahdi Dhaini , Juraj Vladika , Ege Erdogan , Zineb Attaoui , Gjergji Kasneci

Language Models (LMs) have emerged as powerful sources of evidence for linguists seeking to develop theories of syntax. In this paper, we argue that causal interpretability methods, applied to LMs, can greatly enhance the value of such…

Computation and Language · Computer Science 2025-10-01 Sasha Boguraev , Christopher Potts , Kyle Mahowald

The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with…

Artificial Intelligence · Computer Science 2025-12-19 Defu Cao , Michael Gee , Jinbo Liu , Hengxuan Wang , Wei Yang , Rui Wang , Yan Liu

Large language models (LLMs) have recently shown remarkable performance in language tasks and beyond. However, due to their limited inherent causal reasoning ability, LLMs still face challenges in handling tasks that require robust causal…

Computation and Language · Computer Science 2025-03-13 Xin Li , Zhuo Cai , Shoujin Wang , Kun Yu , Fang Chen

Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and…

Machine Learning · Computer Science 2024-12-06 Burak Varıcı , Emre Acartürk , Karthikeyan Shanmugam , Ali Tajer

How does a cause lead to an effect, and which intermediate causal steps explain their connection? This work scrutinizes the mechanistic causal reasoning capabilities of large language models (LLMs) to answer these questions through the task…

Artificial Intelligence · Computer Science 2026-03-19 Liesbeth Allein , Nataly Pineda-Castañeda , Andrea Rocci , Marie-Francine Moens

This article analyzes the use of Large Language Models (LLMs) as support for the conceptual modeling of relational databases through the automatic generation of Entity-Relationship (ER) diagrams from natural language requirements. The…

Artificial Intelligence · Computer Science 2026-05-13 Arthur F. Siqueira , Carlos D. S. Nogueira , Eduarda Farias , Claudio E. C. Campelo , Júlia Menezes

High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most…

Machine Learning · Computer Science 2019-01-07 Vincent Fortuin , Matthias Hüser , Francesco Locatello , Heiko Strathmann , Gunnar Rätsch

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

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after…

Computation and Language · Computer Science 2023-11-14 Sean Xie , Soroush Vosoughi , Saeed Hassanpour

Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A core obstacle is the target data itself: causal systems are…

Artificial Intelligence · Computer Science 2026-05-12 Nicolás Astorga , Anita Kriz , Mihaela van der Schaar

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda