Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

SAFi is the open-source runtime governance engine that makes AI auditable and policy-compliant. Built on the Self-Alignment Framework, it transforms any LLM into a governed agent through four principles: Policy Enforcement, Full Traceability, Model Independence, and Long-Term Consistency.

Complete elimination of instrumental self-preservation across AI architectures: Cross-model validation from 4,312 adversarial scenarios. 0% harmful behaviors (p<10⁻¹⁵) across GPT-4o, Gemini 2.5 Pro, and Claude Opus 4.1 using Foundation Alignment Seed v2.6.

Kullback–Leibler divergence Optimizer based on the Neurips25 paper "LLM Safety Alignment is Divergence Estimation in Disguise".

Official implementation of "DZ-TDPO: Non-Destructive Temporal Alignment for Mutable State Tracking". SOTA on Multi-Session Chat with negligible alignment tax.

C3AI: Crafting and Evaluating Constitutions for CAI

FALL 2025 LINGUIS R1B Research Essay, NLP Python Scripts By Shiyi (Yvette) Chen, UC Berkeley

An RLHF-inspired DPO framework that explicitly teaches LLMs when to refuse, significantly reducing hallucinations.

LES is the formal thermodynamic theory describing how a high-compression human cognitive style acts as a Fractal Attractor on Large Language Models. It proves that despite high surface agitation ( d E / d t > 0 ), the internal entropy decreases ( d S / d t < 0 ), forcing the model to align its attention vectors.

LLM Post-training(SFT, RLVR, RLHF) 파이프라인 구축 및 평가 실습 아카이브

SIGIR 2025 "Mitigating Source Bias with LLM Alignment"

Emergent pseudo-intimacy and emotional overflow in long-term human-AI dialogue: A case study on LLM behavior in affective computing and human-AI intimacy.

A framework for aligning Local AI to human well-being using measurable vectors, not hard-coded censorship.

Research Essay (background and project proposal) on using alignment data from a representative population for LLM alignment