LLM Research

LLM Research

LLM Code Generation Enables Verifiable AI Decision-Making

New research proposes replacing probabilistic LLM outputs with executable code, creating auditable decision trails that could transform AI system trustworthiness and interpretability.

LLM Research

Brittlebench: New Benchmark Measures LLM Fragility to Prompts

New research introduces Brittlebench, a systematic framework for quantifying how sensitive large language models are to minor prompt variations, revealing critical reliability gaps in AI systems.

LLM Research

LLM-Powered Digital Twins Simulate Short-Video Platform Policies

New research combines large language models with digital twin simulations to test content recommendation policies on video platforms before real-world deployment.

LLM Research

New Framework Tests If LLMs Can Truly Reason Like Humans

Researchers propose psychometric validation methods to assess whether large language models genuinely understand psychological concepts or merely pattern-match responses.

LLM Research

New Method Quantifies LLM Uncertainty Using Imprecise Probabiliti

Researchers propose a novel approach for expressing higher-order uncertainty in large language models through imprecise probability theory, moving beyond point estimates to interval-based confidence.

LLM Research

Researchers Discover Chaotic Dynamics in Multi-LLM Systems

New research reveals that multi-LLM deliberation systems can exhibit chaotic dynamics, raising questions about predictability and reliability in AI systems that use multiple models.

LLM Research

Why Multi-LLM Consensus Fails to Verify Truthfulness

New research reveals that using multiple AI models to verify each other's outputs doesn't improve truthfulness—they share the same blind spots, undermining a key assumption in AI verification systems.

LLM Research

New Method Calibrates LLM Confidence to Catch AI Errors

Researchers introduce technique for aligning LLM confidence with actual correctness, enabling better error detection in AI systems and improving reliability for downstream applications.

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 Agents

SkillNet Framework Enables Modular AI Skill Networks

New research introduces SkillNet, a framework for creating, evaluating, and connecting modular AI skills that can be composed into complex agent capabilities.

LLM Research

New Research Exposes LLM Sycophancy in Business Decisions

Researchers analyze how large language models handle ambiguous business scenarios, revealing concerning sycophancy patterns that could undermine AI trustworthiness in enterprise settings.