# CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design

arXiv: https://arxiv.org/abs/2512.02033 · HTML: https://mlsanity.com/paper/2512.02033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 87 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [MatterGen: a generative model for inorganic materials design](https://mlsanity.com/paper/2312.03687/) (2023)
- [Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation](https://mlsanity.com/paper/2410.13640/) (2024)
- [Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning](https://mlsanity.com/paper/2405.14039/) (2024)
- [RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching](https://mlsanity.com/paper/2405.18768/) (2024)
- [De novo PROTAC design using graph-based deep generative models](https://mlsanity.com/paper/2211.02660/) (2022)
- [From Hallucination to Reliability: Generative Modeling and the Structure of Scientific Inference](https://mlsanity.com/paper/2504.08526/) (2025)

## Abstract (arXiv)

Reliable evaluation of protein structure predictions remains challenging, as metrics like pLDDT capture energetic stability but often miss subtle errors such as atomic clashes or conformational traps reflecting topological frustration within the protein folding energy landscape. We present CODE (Chain of Diffusion Embeddings), a self evaluating metric empirically found to quantify topological frustration directly from the latent diffusion embeddings of the AlphaFold3 series of structure predictors in a fully unsupervised manner. Integrating this with pLDDT, we propose CONFIDE, a unified evaluation framework that combines energetic and topological perspectives to improve the reliability of AlphaFold3 and related models. CODE strongly correlates with protein folding rates driven by topological frustration, achieving a correlation of 0.82 compared to pLDDT's 0.33 (a relative improvement of 148%). CONFIDE significantly enhances the reliability of quality evaluation in molecular glue structure prediction benchmarks, achieving a Spearman correlation of 0.73 with RMSD, compared to pLDDT's correlation of 0.42, a relative improvement of 73.8%. Beyond quality assessment, our approach applies to diverse drug design tasks, including all-atom binder design, enzymatic active site mapping, mutation induced binding affinity prediction, nucleic acid aptamer screening, and flexible protein modeling. By combining data driven embeddings with theoretical insight, CODE and CONFIDE outperform existing metrics across a wide range of biomolecular systems, offering robust and versatile tools to refine structure predictions, advance structural biology, and accelerate drug discovery.