English
Related papers

Related papers: Sparse Autoencoders for Hypothesis Generation

200 papers

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Computation and Language · Computer Science 2025-12-02 Ruben Härle , Felix Friedrich , Manuel Brack , Stephan Wäldchen , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and identifying the roles…

Computation and Language · Computer Science 2026-04-21 Nils Feldhus , Laura Kopf

In settings requiring synthetic data generation based on a clinical cohort, e.g., due to data protection regulations, heterogeneity across individuals might be a nuisance that we need to control or faithfully preserve. The sources of such…

Machine Learning · Computer Science 2023-12-14 Kiana Farhadyar , Federico Bonofiglio , Maren Hackenberg , Daniela Zoeller , Harald Binder

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Harrish Thasarathan , Julian Forsyth , Thomas Fel , Matthew Kowal , Konstantinos G. Derpanis

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…

Machine Learning · Computer Science 2025-02-14 Edith Natalia Villegas Garcia , Alessio Ansuini

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…

Machine Learning · Statistics 2019-04-15 Aditya Grover , Stefano Ermon

As language models are increasingly used in scientific workflows, evaluating their ability to propose sets of explanations-not just a single correct answer-becomes critical. Many scientific problems are underdetermined: multiple,…

Computation and Language · Computer Science 2026-03-10 Tingting Chen , Beibei Lin , Zifeng Yuan , Qiran Zou , Hongyu He , Anirudh Goyal , Yew-Soon Ong , Dianbo Liu

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

Machine Learning · Computer Science 2025-05-23 Soham Gadgil , Chris Lin , Su-In Lee

Abstract This project presents a system of neural networks to translate between images and melodies. Autoencoders compress the information in samples to abstract representation. A translation network learns a set of correspondences between…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Karl Wienand , Wolfgang M. Heckl

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Machine Learning · Computer Science 2025-02-06 Abhinav Menon , Manish Shrivastava , David Krueger , Ekdeep Singh Lubana

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Zhengxuan Wu , Jacob Steinhardt , Sarah Schwettmann

We present a method for extracting \emph{monosemantic} neurons, defined as latent dimensions that align with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach employs a Sparse…

Information Retrieval · Computer Science 2025-11-25 Dor Arviv , Yehonatan Elisha , Oren Barkan , Noam Koenigstein

In this paper, we address the knowledge engineering problems for hypothesis generation motivated by applications that require timely exploration of hypotheses under unreliable observations. We looked at two applications: malware detection…

Artificial Intelligence · Computer Science 2014-08-29 Shirin Sohrabi , Octavian Udrea , Anton V. Riabov

As Large Language Models become integral to software development, with substantial portions of AI-suggested code entering production, understanding their internal correctness mechanisms becomes critical for safe deployment. We apply sparse…

Software Engineering · Computer Science 2025-10-06 Kriz Tahimic , Charibeth Cheng

Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the underlying complexity…

Computation and Language · Computer Science 2017-11-27 Anant Subramanian , Danish Pruthi , Harsh Jhamtani , Taylor Berg-Kirkpatrick , Eduard Hovy

AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in…

Artificial Intelligence · Computer Science 2025-01-10 Haokun Liu , Yangqiaoyu Zhou , Mingxuan Li , Chenfei Yuan , Chenhao Tan