Cover Image

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kopf, Laura, Feldhus, Nils, Bykov, Kirill, Bommer, Philine Lou, Hedström, Anna, Höhne, Marina M. -C., Eberle, Oliver
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoSy: Evaluating Textual Explanations of Neurons
by: Kopf, Laura, et al.
Published: (2024)

Interpreting Language Models Through Concept Descriptions: A Survey
by: Feldhus, Nils, et al.
Published: (2025)

Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
by: Bommer, Philine, et al.
Published: (2023)

Deep Learning Meets Teleconnections: Improving S2S Predictions for European Winter Weather
by: Bommer, Philine L., et al.
Published: (2025)

Labeling Neural Representations with Inverse Recognition
by: Bykov, Kirill, et al.
Published: (2023)

A Fresh Look at Sanity Checks for Saliency Maps
by: Hedström, Anna, et al.
Published: (2024)

From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation
by: Wickstrøm, Kristoffer, et al.
Published: (2024)

Simplifying Outcomes of Language Model Component Analyses with ELIA
by: Eidt, Aaron Louis, et al.
Published: (2026)

Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution
by: Eiras-Franco, Carlos, et al.
Published: (2025)

iFlip: Iterative Feedback-driven Counterfactual Example Refinement
by: Wang, Yilong, et al.
Published: (2026)

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
by: Wang, Qianli, et al.
Published: (2025)

Free-text Rationale Generation under Readability Level Control
by: Hsu, Yi-Sheng, et al.
Published: (2024)

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
by: Liu, Weiqi, et al.
Published: (2026)

Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test
by: Hedström, Anna, et al.
Published: (2024)

Proceedings of the ISCA/ITG Workshop on Diversity in Large Speech and Language Models
by: Möller, Sebastian, et al.
Published: (2025)

Explaining Text Similarity in Transformer Models
by: Vasileiou, Alexandros, et al.
Published: (2024)

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
by: Dhaini, Mahdi, et al.
Published: (2025)

CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems
by: Wang, Qianli, et al.
Published: (2024)

Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
by: Gupta, Ayush, et al.
Published: (2025)

Polysemanticity or Polysemy? Lexical Identity Confounds Superposition Metrics
by: Hou, Iyad Ait, et al.
Published: (2026)

Manipulating Feature Visualizations with Gradient Slingshots
by: Bareeva, Dilyara, et al.
Published: (2024)

PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
by: Lu, Zhixiang, et al.
Published: (2025)

Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs
by: Ye, Charles, et al.
Published: (2026)

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
by: Sun, Jingyi, et al.
Published: (2026)

Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence
by: Gong, Bofan, et al.
Published: (2025)

Persona Prompting as a Lens on LLM Social Reasoning
by: Yang, Jing, et al.
Published: (2026)

Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
by: Frei, Johann, et al.
Published: (2025)

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
by: Wang, Qianli, et al.
Published: (2024)

Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
by: Linhardt, Lorenz, et al.
Published: (2025)

PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers
by: Loc, Ngoc Phan Phuoc, et al.
Published: (2026)

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification
by: Yu, Wenlong, et al.
Published: (2025)

Multi-Intent Recognition in Dialogue Understanding: A Comparison Between Smaller Open-Source LLMs
by: Ahmad, Adnan, et al.
Published: (2025)

PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards
by: Ghimire, Mukesh, et al.
Published: (2026)

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
by: Wang, Qianli, et al.
Published: (2024)

Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
by: Karamolegkou, Antonia, et al.
Published: (2025)

Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations
by: Brandl, Stephanie, et al.
Published: (2024)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
by: Wang, Qianli, et al.
Published: (2026)

PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
by: Nahid, Md Mahadi Hasan, et al.
Published: (2025)

Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
by: Wang, Qianli, et al.
Published: (2025)

Explaining Bayesian Neural Networks
by: Bykov, Kirill, et al.
Published: (2021)