Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
A Bayesian Approach to Quantify the Uncertainty of Human Ratings in a Single-Instance Multimodal Framework
Zijian Chen, Archana Venkataraman
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add rating-uncertainty variable U (ablation) | Full model · Synthetic (standard generator) | RMSE_X: 0.853 -> 0.694 | Improved |
| add rating-uncertainty variable U (ablation) | Full model · Synthetic (standard generator) | RMSE_Y: 0.462 -> 0.455 | No clear effect |
| add feature-selection mask M (ablation) | Full model · Synthetic (standard generator) | RMSE_Y: 0.716 -> 0.455 | Improved |
| add both U and M (ablation) | Full model · Synthetic (standard generator) | R2_Z: 0.931 -> 0.999 | Improved |
| harder corruption of auxiliary data (Hard-M) | Full model · Synthetic | RMSE_Y: 0.455 -> 1.155 | Hurt |
| more label ambiguity (Hard-U) | Full model · Synthetic | RMSE_X: 0.694 -> 0.793 | Hurt |
| less separable latent clusters (Hard-Z) | Full model · Synthetic | R2_Z: 0.999 -> 0.861 | Hurt |
| proposed framework vs best multimodal baseline | Ours vs MoPoE · ABIDE I/II (validation) | RMSE_X (reconstruction): 5.016 -> 2.448 | Improved |
| proposed framework vs best interval baseline | Ours vs Deep Ens · ABIDE I/II (validation) | MPIW90: 13.597 -> 10.473 | Improved |
| proposed framework vs Deep Ensembles on held-out ACE | Ours vs Deep Ens · ACE (test) | R2_X,pred: 0.501 vs 0.589 | Hurt |
Closest papers by meaning
- BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments (NeurIPS 2026 · similarity 0.87)
- Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge (ICLR 2025 · similarity 0.84)
- Bridging Human and LLM Judgments: Understanding and Narrowing the Gap (NeurIPS 2025 · similarity 0.83)
- Quantifying Uncertainty in Error Consistency: Towards Reliable Behavioral Comparison of Classifiers (NeurIPS 2025 · similarity 0.82)
- Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment (NeurIPS 2026 · similarity 0.82)
- An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
