AI Alignment

LLM Research

AI Steerability 360: New Toolkit for Controlling LLM Behavior

Researchers introduce AI Steerability 360, a comprehensive toolkit enabling multiple techniques for steering large language model outputs with implications for content control and AI safety.

AI Safety

New Research Exposes How LLMs Strategically Deceive in Games

Researchers develop parallel-world probing technique to detect when large language models strategically lie during human-AI interactions, revealing concerning deceptive capabilities.

AI Safety

Research: LLM Safety Training Survives RL Optimization

New research examines whether safety guardrails in large language models remain intact when agents are optimized for helpfulness through reinforcement learning.

mechanistic interpretability

Mechanistic Tracing Reveals How LLMs Navigate Pain-Pleasure Decis

New research goes beyond behavioral analysis to trace the internal mechanisms LLMs use when weighing competing reward signals, offering insights into AI decision-making at the circuit level.

LLM safety

Can Parameter Region Constraints Make LLMs Safer?

New research explores whether constraining specific parameter regions in large language models can ensure safety, examining the theoretical foundations of alignment through architectural constraints.

AI Safety

4 AI Safety Alignment Methods: Building Trustworthy AI Systems

From RLHF to Constitutional AI, these four technical approaches aim to prevent AI systems from lying, manipulating, or causing harm—critical foundations for trustworthy synthetic media.

LLM safety

Selective Geometry Control: A New Approach to LLM Safety

New research proposes geometric methods to enhance LLM safety alignment robustness, offering potential improvements for AI systems that moderate synthetic media and deepfake content.

AI Safety

Research Explores How Information Access Shapes AI Sabotage Detec

New arXiv research investigates how varying levels of information access affect LLM monitors' ability to detect sabotage, with implications for AI safety and oversight systems.

AI Alignment

Multi-Model Dialogical Framework Tests AI Alignment Strategies

New research introduces a framework using dialogical reasoning across different AI architectures to systematically evaluate and compare alignment strategies.

LLM Research

Sparse Autoencoders Enable Fine-Grained Control of LLM Reasoning

New research demonstrates how Sparse Autoencoders can steer LLM reasoning processes, enabling precise control over chain-of-thought behavior without retraining models.

AI Safety

New Research Proposes Behavioral Guidance for Trustworthy AI Agen

Researchers present a framework for making multi-turn LLM agents more trustworthy through behavioral guidance, addressing critical safety concerns as AI systems become more autonomous.

AI Security

AI Security Battles: Is Robust Alignment an Endless Struggle?

New research examines whether AI security and alignment efforts face fundamental limitations, analyzing the cycle of safety measures and adversarial bypasses in modern AI systems.