# Talk Less, Verify More: Improving LLM Assistants with Semantic Checks and Execution Feedback

arXiv: https://arxiv.org/abs/2601.00224 · HTML: https://mlsanity.com/paper/2601.00224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 1 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [The Generative AI Paradox: "What It Can Create, It May Not Understand"](https://mlsanity.com/paper/2311.00059/) (2023)
- [Evaluation of Task Specific Productivity Improvements Using a Generative Artificial Intelligence Personal Assistant Tool](https://mlsanity.com/paper/2409.14511/) (2024)

## Abstract (arXiv)

As large language model (LLM) assistants become increasingly integrated into enterprise workflows, their ability to generate accurate, semantically aligned, and executable outputs is critical. However, current conversational business analytics (CBA) systems often lack built-in verification mechanisms, leaving users to manually validate potentially flawed results. This paper introduces two complementary verification techniques: Q*, which performs reverse translation and semantic matching between code and user intent, and Feedback+, which incorporates execution feedback to guide code refinement. Embedded within a generator-discriminator framework, these mechanisms shift validation responsibilities from users to the system. Evaluations on three benchmark datasets, Spider, Bird, and GSM8K, demonstrate that both Q* and Feedback+ reduce error rates and task completion time. The study also identifies reverse translation as a key bottleneck, highlighting opportunities for future improvement. Overall, this work contributes a design-oriented framework for building more reliable, enterprise-grade GenAI systems capable of trustworthy decision support.