From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations

arXiv:2608.25894 · cs.CL · Submitted 2026-08-26 · Read on arXiv

cs.CL

Submitted: 2026-08-26

Updated: 2026-08-26

Comments: Accepted to the Main Conference of EMNLP 2026

Code: https://github.com/WangPing-Kayla/Deduce

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 38× in this paper · explained in 1 episode
• Hallucination — 31× in this paper · explained in 3 episodes
• Robustness — 16× in this paper · explained in 5 episodes
• Clarification Score — 13× in this paper
• Benchmark — 12× in this paper · explained in 2 episodes
• Arbiter — 11× in this paper · explained in 1 episode
• Verification — 9× in this paper · explained in 2 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Hallucination Mitigation — 6× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Correction Rate — 4× in this paper
• Misleading Rate — 4× in this paper
• LLM judge — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Sycophancy — 3× in this paper · explained in 4 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes

Sources

• Reducing hallucination in structured outputs via Retrieval-Augmented Generation
• Integrative Decoding: Improve Factuality via Implicit Self-consistency
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
• The Llama 3 Herd of Models
• How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation
• Textbooks Are All You Need II: phi-1.5 technical report
• Towards Mitigating Hallucination in Large Language Models via Self-Reflection
• Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
• LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
• Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
• ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
• Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
• JudgeBench: A Benchmark for Evaluating LLM-based Judges
• Knowledge Conflicts for LLMs: A Survey
• Qwen2.5 Technical Report
• Gemma: Open Models Based on Gemini Research and Technology
• A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
• FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
• Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering