Blog

a look inside my head

Literature Review: The Hidden Dimensions of LLM Alignment

3 min read · August 16, 2025

2025 · LLM Interpretability Trustworthy AI Safety Alignment Adversarial AI · research
Literature Review: Jailbreak Antidote – Runtime Safety-Utility Balance via Sparse Representation Adjustment

3 min read · August 16, 2025

2025 · Adversarial AI Trustworthy AI LLM Mechanistic Interpretability Representation Engineering · research
Literature Review: Refusal Behavior in Large Language Models: A Nonlinear Perspective

3 min read · August 16, 2025

2025 · LLM AI Alignment Interpretability Trustworthy AI · research
Literature Review: Context Rot — How Increasing Input Tokens Impacts LLM Performance

3 min read · August 10, 2025

2025 · LLM Retrieval-Augmented Generation Prompt Engineering · research
Literature Review: Dissecting Recall of Factual Associations in Auto-Regressive Language Models

3 min read · August 10, 2025

2025 · Mechanistic Interpretability LLM · research