Averaging Bias: Human Faithfulness Annotations are not Locally Faithful

arXiv:2608.00205 · cs.CL · Submitted 2026-07-31 · Read on arXiv

Huajian Zhang, Yiyang Feng, Jiawei Zhou

cs.CL

Submitted: 2026-07-31

Code: https://github.com/Zesearch/human-annotation-averging-bias

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

Terminology

• Benchmark — 74× in this paper · explained in 2 episodes
• Faithfulness — 48× in this paper · explained in 2 episodes
• Consistency — 23× in this paper · explained in 3 episodes
• LLM judge — 18× in this paper · explained in 2 episodes
• Papers — 15× in this paper · explained in 3 episodes
• AUC — 11× in this paper · explained in 2 episodes
• Hallucination — 9× in this paper · explained in 4 episodes
• Abstractive Summarization — 5× in this paper · explained in 1 episode
• Adam — 4× in this paper · explained in 3 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Composition — 3× in this paper · explained in 2 episodes
• Coherence — 2× in this paper · explained in 2 episodes
• Conditional Independence — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Augmentation — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 9 episodes
• Cognitive Load — 1× in this paper · explained in 2 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• Judge Reliability — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 4 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Verifiability — 1× in this paper · explained in 3 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• Understanding Retrieval Augmentation for Long-Form Question Answering
• Olmo 3
• Qwen3 Technical Report

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