Too Good to Be Real? Diagnosing and Reducing the Gap Between AI Preference and Real User Engagement
cs.CL
Submitted: 2026-09-16
Updated: 2026-09-16
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Explaining Length Bias in LLM-Based Preference Evaluations
- Preference Leakage: A Contamination Problem in LLM-as-a-judge
- Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- Verbosity Bias in Preference Labeling by Large Language Models
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Calibrating Model-Based Evaluation Metrics for Summarization
- Learning to Control Summaries with Score Ranking
- LLaMA: Open and Efficient Foundation Language Models
- Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction
- Self-Preference Bias in LLM-as-a-Judge
- HotComment: A Benchmark for Evaluating Popularity of Online Comments
- Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse
- ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
- Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation
- IntervenSim: Intervention-Aware Social Network Simulation for Opinion Dynamics
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