From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations
Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input. Existing approaches to hallucination mitigation typically assume reliable user inputs, overlooking how such factual errors can actively mislead model reasoning. To address this vulnerability, we propose DEDUCE, a three-stage framework that transforms LLMs from passive responders into proactive error correctors. DEDUCE operates in three stages: (1) detect errors through fine-grained fact extraction
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%google-research/google-research →
“Shared author/contributor keys: sun”
- LinkedLinked via arxiv author · 85%Wenping Wang →
“From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations”
- LinkedLinked via arxiv author · 85%Xiangguo Sun →
“From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations”
- LinkedLinked via arxiv author · 85%Bingbing Xu →
“From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations”
- LinkedLinked via arxiv author · 85%Guocong Li →
“From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations”
- LinkedLinked via arxiv author · 85%Xiaofeng Meng →
“From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations”