People-Centered Computing Lab
  • Home
  • People
  • Research
  • Education
  • Publications
  • Datasets
  • News
  • Positions
  • Contact
ESC

Searching...

No results found

↑↓ Navigate ↵ Select
Powered by Hugo Blox
  • Open Positions
  • Research
    • XAI-FinCrime
    • EXperiMental: Wearable Technology and EXplainable AI for Mental Health and Inclusivity in Schools
    • XAI-PAC: Towards Explainable and Private Affective Computing
    • TRUST-ME: TRUstworthy enhancement of job SaTisfaction and productivity using Micro-sensing in work Environments
    • SmartCHANGE
    • PROSELF: Semi-automated Self-Tracking Systems to Improve Personal Productivity
    • BASE: Behavioral Analytics for Smart Environments
    • From Sharing to Caring: Examining Socio-Technical Aspects of the Collaborative Economy
    • Uncovering Privacy Concerns for Public Display Personalisation
    • PersonAAL: Improving Quality of Life and Remote Care
    • SHARING21: Future Digital Sharing Interfaces
    • CYBERPARKS: ICT and Public Spaces
    • RECALL: Enhanced Human Memory
    • APD: Attentive Public Displays
    • SAPIENT: Supporting Fundamental Rights, Privacy and Ethics in Surveillance Technologies
    • PD-NET: Towards Future Pervasive Display Networks
    • PALS: Privacy-Aware Location Sharing
    • LiSS: Living in Surveillance Societies
  • News
    • PhD position: XAI-FinCrime
    • Postdoc position: XAI-FinCrime
    • Prof. Silvia Santini’s contribution on La Regione
    • Our group members ranked among the world’s top 2% of scientists
    • Daniel Gatica-Perez presents Towards Increasing Diversity in Mobile Sensing Research
    • Prof. Marc Langheinrich’s contribution on La Regione
    • Tutorial at the Neuroergonomics 2021 conference in Munich
    • Martin to win Jožef Stefan Prize!
    • IEEE Pervasive: Oct-Dec 2020 issue is out!
  • Datasets
    • LIFETRACE
    • LAUREATE
    • BiHeartS
    • HeartS
    • M2Sleep
    • HAFAR
    • EDArtifact
    • USILaughs
  • Contact
  • Courses
  • Education
  • Student Projects
  • Navigate
  • Home
  • People
  • Research
  • Education
  • Publications
  • Datasets
  • News
  • Positions
  • Contact

Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP

Jan 1, 2025·
Francesco Sovrano
Francesco Sovrano
· 0 min read
URL DOI
Type
Journal article
Publication
CoRR
publications
Last updated on Jan 1, 2025
Authors
Francesco Sovrano
Francesco Sovrano
Postdoc
← Blue Mondays and Happy Meals: Investigating the Impact of Contextual Factors on Mood States Jan 1, 2025
Categorical Explaining Functors: Ensuring Coherence in Logical Explanations Jan 1, 2025 →

© 2026 Università della Svizzera italiana · Faculty of Informatics. This work is licensed under CC BY NC ND 4.0

Made with Hugo Blox. Create yours →