Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
This addresses the issue of unreliable structured outputs for enterprise AI applications, enabling more efficient human review, though it is incremental as it builds on existing scoring methods.
The paper tackles the problem of sporadic errors in LLM structured outputs by presenting CONSTRUCT, a method for real-time trustworthiness scoring that identifies lower-scoring outputs likely to contain errors, achieving significantly higher precision/recall than other methods on a four-dataset benchmark.
Structured Outputs from current LLMs exhibit sporadic errors, hindering enterprise AI efforts from realizing their immense potential. We present CONSTRUCT, a method to score the trustworthiness of LLM Structured Outputs in real-time, such that lower-scoring outputs are more likely to contain errors. This reveals the best places to focus limited human review bandwidth. CONSTRUCT additionally scores the trustworthiness of each field within a LLM Structured Output, helping reviewers quickly identify which parts of the output are wrong. Our method is suitable for any LLM (including black-box LLM APIs without logprobs such as reasoning models and Anthropic models), does not require labeled training data nor custom model deployment, and works for complex Structured Outputs with many fields of diverse types (including nested JSON schemas). We additionally present one of the first public LLM Structured Output benchmarks with reliable ground-truth values that are not full of mistakes. Over this four-dataset benchmark, CONSTRUCT detects errors from various LLMs (including Gemini 3 and GPT-5) with significantly higher precision/recall than other scoring methods.