English
Related papers

Related papers: Model Directions, Not Words: Mechanistic Topic Mod…

200 papers

We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify "summary-worthy" words. Concretely, a series of unsupervised topic models is explored and experimental results…

Computation and Language · Computer Science 2016-06-28 Lu Wang , Claire Cardie

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

Topic models are widely used to analyze document collections. While they are valuable for discovering latent topics in a corpus when analysts are unfamiliar with the corpus, analysts also commonly start with an understanding of the content…

Computation and Language · Computer Science 2024-07-01 Garima Dhanania , Sheshera Mysore , Chau Minh Pham , Mohit Iyyer , Hamed Zamani , Andrew McCallum

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

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

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i.e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order…

Computation and Language · Computer Science 2019-02-26 Pankaj Gupta , Yatin Chaudhary , Florian Buettner , Hinrich Schütze

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) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree…

Computation and Language · Computer Science 2016-12-22 Peixian Chen , Nevin L. Zhang , Tengfei Liu , Leonard K. M. Poon , Zhourong Chen , Farhan Khawar

Understanding source code is a topic of great interest in the software engineering community, since it can help programmers in various tasks such as software maintenance and reuse. Recent advances in large language models (LLMs) have…

Software Engineering · Computer Science 2025-04-25 Michele Carissimi , Martina Saletta , Claudio Ferretti

Over the years, topic models have provided an efficient way of extracting insights from text. However, while many models have been proposed, none are able to model topic temporality and hierarchy jointly. Modelling time provide more precise…

Information Retrieval · Computer Science 2023-01-25 Judicael Poumay , Ashwin Ittoo

Since the advent of machine learning, interpretability has remained a persistent challenge, becoming increasingly urgent as generative models support high-stakes applications in drug and material discovery. Recent advances in large language…

Machine Learning · Computer Science 2025-12-10 Jaron Cohen , Alexander G. Hasson , Sara Tanovic

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…

Computation and Language · Computer Science 2020-08-12 Lixing Zhu , Yulan He , Deyu Zhou

Topic models have been widely used to learn text representations and gain insight into document corpora. To perform topic discovery, most existing neural models either take document bag-of-words (BoW) or sequence of tokens as input followed…

Computation and Language · Computer Science 2021-07-12 Madhur Panwar , Shashank Shailabh , Milan Aggarwal , Balaji Krishnamurthy

Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability seeks to mitigate the issues through extracts…

Machine Learning · Computer Science 2026-01-30 Yuhang Liu , Erdun Gao , Dong Gong , Anton van den Hengel , Javen Qinfeng Shi

While Transformer language models (LMs) are state-of-the-art for information extraction, long text introduces computational challenges requiring suboptimal preprocessing steps or alternative model architectures. Sparse attention LMs can…

Computation and Language · Computer Science 2022-12-01 Joel Stremmel , Brian L. Hill , Jeffrey Hertzberg , Jaime Murillo , Llewelyn Allotey , Eran Halperin

Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret.…

Computation and Language · Computer Science 2021-06-18 Federico Bianchi , Silvia Terragni , Dirk Hovy

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant
‹ Prev 1 4 5 6 7 8 10 Next ›