Holistic AI Papers

CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries

Bias Amplification: Large Language Models as Increasingly Biased Media

From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs

State of AI Regulations in 2025: Everything you need to know

THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models

HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection

Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics