# VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence

arXiv: https://arxiv.org/abs/2610.00833 · HTML: https://mlsanity.com/paper/2610.00833/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [Semantic Noise Matters for Neural Natural Language Generation](https://mlsanity.com/paper/1911.03905/) (2019)
- [Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings](https://mlsanity.com/paper/1606.05491/) (2016)
- [A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation](https://mlsanity.com/paper/1805.06553/) (2018)

## Abstract (arXiv)

Fluent LLM explanations may not follow the evidence from a structured system. We present VERITYGATE, a four-gate checker for declared evidence IDs, entities, numbers, and claim types. It checks a fixed schema; it does not verify every fact in the prose. At r=0 and r=1, we test 900 instances per setting (450 grounded-ungrounded pairs) with GPT-4o-mini, Llama-3.3-70B, and Claude Sonnet 4.6. Under this schema-level contract and before repair, 80.3% of mini claims and 47.9% of Sonnet claims fail. These are verifier rejection rates, not prose-hallucination rates. One repair pass raises claim survival from 19.7% to 28.0% for mini and from 52.1% to 54.3% for Sonnet. Verified claims per example change by +0.14 for mini, -0.71 for Llama, and -0.47 for Sonnet, so survival and output volume must be reported together. A second Sonnet pass gives no clear gain. At r=1, Gate 4 covers 97.0%, 98.7%, and 100% of failing claims for mini, Llama, and Sonnet. Small human studies support the rules but show gaps between schema checks and correct prose. A domain-specific GPT-4o judge test shows an order effect, so it is only a usefulness check. We release the code and data.