Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations
Fragile Reasoning: A Mechanistic Analysis of LLM Sensitivity to Meaning-Preserving Perturbations explores This research develops a framework to diagnose and fix the surprising fragility of large language models to meaning-preserving text changes, offering a path to more reliable AI.. Commercial viability score: 7/10 in LLM Robustness.
Updated 4 hours ago
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisThe Fragility Of Moral Judgment In Large Language ModelsViability: 3.0
- Builds On ThisSame Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM EvaluationViability: 4.0
- Builds On ThisSemantic Invariance in Agentic AIViability: 5.0
- Builds On ThisFrom Early Encoding to Late Suppression: Interpreting LLMs on Character Counting TasksViability: 4.0
- Builds On ThisFinding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency VerificationViability: 5.0