Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization

arXiv:2605.28802 · cs.CL · Submitted 2026-05-27 · Read on arXiv

cs.CL

Submitted: 2026-05-27

Updated: 2026-08-28

Comments: Accepted by EMNLP 2026 Main, 46 pages, 20 figures

Code: https://github.com/mainlp/CAPO

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

Terminology

• Aggregation — 40× in this paper
• Accuracy — 36× in this paper · explained in 1 episode
• Embeddings — 31× in this paper · explained in 2 episodes
• Ablation — 19× in this paper · explained in 1 episode
• Alignment — 12× in this paper
• Core — 11× in this paper · explained in 2 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Lexical Diversity — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Actor — 3× in this paper · explained in 3 episodes
• Redundancy — 3× in this paper · explained in 2 episodes
• Annotator Agreement — 2× in this paper
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Distribution Shift — 2× in this paper · explained in 9 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 8 episodes
• Semantic Alignment — 2× in this paper · explained in 4 episodes
• Semantic Similarity — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Activation Steering — 1× in this paper · explained in 5 episodes
• Active Learning — 1× in this paper · explained in 6 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning — 1× in this paper · explained in 7 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 6 episodes
• Low-Resource Languages — 1× in this paper · explained in 4 episodes
• Natural Language Inference (NLI) — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 5 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper

Sources

• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
• Out of One, Many: Using Language Models to Simulate Human Samples
• ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
• Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
• Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations
• Entropy and type-token ratio in gigaword corpora
• The Llama 3 Herd of Models
• Qwen3 Technical Report
• Steering Language Models With Activation Engineering
• EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI

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