Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness

arXiv:2610.00568 · cs.CL, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/uiuc-conversational-ai-lab/Emergent-unfaithfulness

Project page: https://uiuc-conversational-ai-lab.github.io/Emergent-unfaithfulness

Terminology

• Alignment — 50× in this paper · explained in 1 episode
• Trace — 14× in this paper · explained in 2 episodes
• Hallucination — 10× in this paper · explained in 3 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• LLM judge — 6× in this paper · explained in 2 episodes
• Annotator Agreement — 5× in this paper · explained in 1 episode
• Interpretability — 5× in this paper · explained in 15 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Steering — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Faithful Preference Gap — 3× in this paper
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Error Taxonomy — 2× in this paper · explained in 2 episodes
• Faithful Preference Rate — 2× in this paper
• In-Context Learning — 2× in this paper · explained in 4 episodes
• RAG — 2× in this paper · explained in 3 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Steering — 1× in this paper · explained in 4 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Intelligence Advanced Research Projects Activity — 1× in this paper
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Office of the Director of National Intelligence — 1× in this paper
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Using Faithfulness Preference Analysis — 1× in this paper

Sources

• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Constitutional AI: Harmlessness from AI Feedback
• Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
• DeepSeek-V3 Technical Report
• The Llama 3 Herd of Models
• Olmo 3
• Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
• GPT-4o System Card
• Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
• Towards Faithful Model Explanation in NLP: A Survey
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Are Emergent Abilities of Large Language Models a Mirage?
• Why Do Some Language Models Fake Alignment While Others Don't?
• FaithLens: Detecting and Explaining Faithfulness Hallucination
• ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
• Emergent Abilities of Large Language Models
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model

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