Cover Image

Sparse Autoencoders for Hypothesis Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Movva, Rajiv, Peng, Kenny, Garg, Nikhil, Kleinberg, Jon, Pierson, Emma
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Computers and Society
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts
by: Peng, Kenny, et al.
Published: (2025)

Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers
by: Movva, Rajiv, et al.
Published: (2023)

How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
by: Garg, Nikhil, et al.
Published: (2026)

What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
by: Movva, Rajiv, et al.
Published: (2025)

Correlated Errors in Large Language Models
by: Kim, Elliot, et al.
Published: (2025)

A No Free Lunch Theorem for Human-AI Collaboration
by: Peng, Kenny, et al.
Published: (2024)

Generative AI in Medicine
by: Shanmugam, Divya, et al.
Published: (2024)

Annotation alignment: Comparing LLM and human annotations of conversational safety
by: Movva, Rajiv, et al.
Published: (2024)

Hypothesis Generation with Large Language Models
by: Zhou, Yangqiaoyu, et al.
Published: (2024)

HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation
by: Liu, Haokun, et al.
Published: (2025)

Literature Meets Data: A Synergistic Approach to Hypothesis Generation
by: Liu, Haokun, et al.
Published: (2024)

Learning Disease Progression Models That Capture Health Disparities
by: Chiang, Erica, et al.
Published: (2024)

Language Generation in the Limit
by: Kleinberg, Jon, et al.
Published: (2024)

Position: The Most Expensive Part of an LLM should be its Training Data
by: Kandpal, Nikhil, et al.
Published: (2025)

Evaluating the World Model Implicit in a Generative Model
by: Vafa, Keyon, et al.
Published: (2024)

Modeling the Economic Impacts of AI Openness Regulation
by: Qiu, Tori, et al.
Published: (2025)

The Backfiring Effect of Weak AI Safety Regulation
by: Laufer, Benjamin, et al.
Published: (2025)

The Lock-in Hypothesis: Stagnation by Algorithm
by: Qiu, Tianyi Alex, et al.
Published: (2025)

The Ontological Dissonance Hypothesis: AI-Triggered Delusional Ideation as Folie a Deux Technologique
by: Lipinska, Izabela, et al.
Published: (2025)

Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
by: Xiong, Guangzhi, et al.
Published: (2025)

Superficial Safety Alignment Hypothesis
by: Li, Jianwei, et al.
Published: (2024)

ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discrimination and Stereotyping
by: Bahl, Rajiv, et al.
Published: (2025)

A Bayesian Spatial Model to Correct Under-Reporting in Urban Crowdsourcing
by: Agostini, Gabriel, et al.
Published: (2023)

Constrain Alignment with Sparse Autoencoders
by: Yin, Qingyu, et al.
Published: (2024)

In your own words: computationally identifying interpretable themes in free-text survey data
by: Wang, Jenny S, et al.
Published: (2026)

The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances
by: Nie, Allen, et al.
Published: (2024)

Beyond Instrumental and Substitutive Paradigms: Introducing Machine Culture as an Emergent Phenomenon in Large Language Models
by: Hu, Yueqing, et al.
Published: (2026)

Clinical Note Bloat Reduction for Efficient LLM Use
by: Cahoon, Jordan L., et al.
Published: (2026)

From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models
by: Alsagheer, Dana, et al.
Published: (2025)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
by: Shu, Huizhen, et al.
Published: (2025)

Emissions and Performance Trade-off Between Small and Large Language Models
by: Garg, Anandita, et al.
Published: (2025)

Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff
by: Greenwood, Sophie, et al.
Published: (2025)

SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
by: Liu, Dengcan, et al.
Published: (2025)

Explainability and Certification of AI-Generated Educational Assessments
by: Yaacoub, Antoun, et al.
Published: (2026)

Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face
by: Laufer, Benjamin, et al.
Published: (2025)

The Responsible Development of Automated Student Feedback with Generative AI
by: Lindsay, Euan D, et al.
Published: (2023)

Measuring Human Contribution in AI-Assisted Content Generation
by: Xie, Yueqi, et al.
Published: (2024)

Effect of Gender Fair Job Description on Generative AI Images
by: Böckling, Finn, et al.
Published: (2025)

General Scales Unlock AI Evaluation with Explanatory and Predictive Power
by: Zhou, Lexin, et al.
Published: (2025)

Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation
by: Zugecova, Aneta, et al.
Published: (2024)