English
Related papers

Related papers: Extracting Interaction-Aware Monosemantic Concepts…

200 papers

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Computation and Language · Computer Science 2025-07-01 Ananya Joshi , Celia Cintas , Skyler Speakman

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

Instruction tuning improves the ability of large language models (LLMs) to follow diverse human instructions, but achieving strong performance on specific target tasks remains challenging. A critical bottleneck is selecting the most…

Machine Learning · Computer Science 2025-05-19 Da Ma , Gonghu Shang , Zhi Chen , Libo Qin , Yijie Luo , Lei Pan , Shuai Fan , Lu Chen , Kai Yu

Autoencoder recommenders have recently shown state-of-the-art performance in the recommendation task due to their ability to model non-linear item relationships effectively. However, existing autoencoder recommenders use fully-connected…

Information Retrieval · Computer Science 2020-08-19 Farhan Khawar , Leonard Kin Man Poon , Nevin Lianwen Zhang

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

Recommendation model interpretation aims to reveal the relationships between inputs, model internal representations and outputs to enhance the transparency, interpretability, and trustworthiness of recommendation systems. However, the…

Information Retrieval · Computer Science 2026-01-27 Jiayin Wang , Xiaoyu Zhang , Weizhi Ma , Zhiqiang Guo , Min Zhang

Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity…

Information Retrieval · Computer Science 2024-06-18 Mingming Li , Fuqing Zhu , Feng Yuan , Songlin Hu

Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, interpretable concepts. However, standard training objectives…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Ali Nasiri-Sarvi , Anh Tien Nguyen , Hassan Rivaz , Dimitris Samaras , Mahdi S. Hosseini

The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…

Machine Learning · Computer Science 2026-01-29 Chiraag Kaushik , Davis Barch , Andrea Fanelli

We present neuron embeddings, a representation that can be used to tackle polysemanticity by identifying the distinct semantic behaviours in a neuron's characteristic dataset examples, making downstream manual or automatic interpretation…

Machine Learning · Computer Science 2024-11-14 Alex Foote

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Computation and Language · Computer Science 2026-03-26 Wilson E. Marcílio-Jr , Danilo M. Eler

Multimodal recommendation systems have attracted increasing attention for their improved performance by leveraging items' multimodal information. Prior methods often build modality-specific item-item semantic graphs from raw modality…

Information Retrieval · Computer Science 2025-08-11 Xiaoxiong Zhang , Xin Zhou , Zhiwei Zeng , Dusit Niyato , Zhiqi Shen

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Computation and Language · Computer Science 2025-06-03 Mark Muchane , Sean Richardson , Kiho Park , Victor Veitch

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

Computation and Language · Computer Science 2025-07-10 Shun Wang , Tyler Loakman , Youbo Lei , Yi Liu , Bohao Yang , Yuting Zhao , Dong Yang , Chenghua Lin

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

To better interpret the intrinsic mechanism of large language models (LLMs), recent studies focus on monosemanticity on its basic units. A monosemantic neuron is dedicated to a single and specific concept, which forms a one-to-one…

Computation and Language · Computer Science 2024-10-17 Hanqi Yan , Yanzheng Xiang , Guangyi Chen , Yifei Wang , Lin Gui , Yulan He

Popularity bias is a well-known challenge in recommender systems, where a small number of popular items receive disproportionate attention, while the majority of less popular items are largely overlooked. This imbalance often results in…

Information Retrieval · Computer Science 2025-08-26 Parviz Ahmadov , Masoud Mansoury

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Laura O'Mahony , Vincent Andrearczyk , Henning Muller , Mara Graziani

Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as accidental interactions, leading to suboptimal performance.…

Information Retrieval · Computer Science 2025-10-07 Tongzhou Wu , Yuhao Wang , Maolin Wang , Chi Zhang , Xiangyu Zhao