Natural Language Interfaces for Databases em-power non-technical users to interact with data using natural language (NL). Advanced approaches, utilizing either neural sequence-to-sequence or more recent sophisticated large-scale language models, typically implement NL to SQL (NL2SQL) translation in an end-to-end fashion. However, like humans, these end-to-end translation models may not always generate the best SQL output on their first try. In this paper, we propose Cyclesql, an iterative framework designed for end-to-end translation models to autonomously generate the best output through self-evaluation. The main idea of CyClesqlis to introduce data-grounded NL explanations of query results as self-provided feedback, and use the feedback to validate the correctness of the translation iteratively, hence improving the overall translation accuracy. Extensive experiments, including quantitative and qualitative evaluations, are conducted to study Cyclesql by applying it to seven existing translation models on five widely used benchmarks. The results show that 1) the feedback loop introduced in Cyclesql can consistently improve the performance of existing models, and in particular, by applying Cyclesql to Resdsql, obtains a translation accuracy of 82.0% (+2.6 %) on the validation set, and 81.6 % (+3.2 %) on the test set of Spider benchmark; 2) the generated NL explanations can also provide insightful information for users, aiding in the comprehension of translation results and consequently enhancing the interpretability of NL2SQL translation11Our code is available at https://github.com/Kaimary/CycleSQL..

The Natural Language Interface to Databases (NLIDB) empowers non-technical users with database access through intuitive natural language (NL) interactions. Advanced approaches, utilizing neural sequence-to-sequence models or large-scale language models, typically employ auto-regressive decoding to generate unique SQL queries sequentially. While these translation models have greatly improved the overall translation accuracy, surpassing 70% on NLIDB benchmarks, the use of auto-regressive decoding to generate single SQL queries may result in sub-optimal outputs, potentially leading to erroneous translations. In this paper, we propose Metasql, a unified generate-then-rank framework that can be flexibly incorporated with existing NLIDBs to consistently improve their translation accuracy. Metasql introduces query metadata to control the generation of better SQL query candidates and uses learning-to-rank algorithms to retrieve globally optimized queries. Specifically, Metasql first breaks down the meaning of the given NL query into a set of possible query metadata, representing the basic concepts of the semantics. These metadata are then used as language constraints to steer the underlying translation model toward generating a set of candidate SQL queries. Finally, Metasql ranks the candidates to identify the best matching one for the given NL query. Extensive experiments are performed to study Metasql on two public NLIDB benchmarks. The results show that the performance of the translation models can be effectively improved using Metasql. In particular, applying Metasql to the published Lgesql model obtains a translation accuracy of 77.4 % on the validation set and 72.3 % on the test set of the Spider benchmark, outperforming the baseline by 2.3% and 0.3%, respectively. Moreover, applying Metasql to GpT-4 achieves translation accuracies of 68.6%, 42.0%, and 17.6 % on the three real-world complex scientific databases of Sciencebenchmark, respectively. The code for Metasql is available at https://github.com/Kaimary/MetaSQL.

Large Language Model (LLM) techniques play an increasingly important role in Natural Language to SQL (NL2SQL) translation. LLMs trained by extensive corpora have strong natural language understanding and basic SQL generation abilities without additional tuning specific to NL2SQL tasks. Existing LLMs-based NL2SQL approaches try to improve the translation by enhancing the LLMs with an emphasis on user intention understanding. However, LLMs sometimes fail to generate appropriate SQL due to their lack of knowledge in organizing complex logical operator composition. A promising method is to input the LLMs with demonstrations, which include known NL2SQL translations from various databases. LLMs can learn to organize operator compositions from the input demonstrations for the given task. In this paper, we propose PURPLE (Pre-trained models Utilized to Retrieve Prompts for Logical Enhancement), which improves accuracy by retrieving demonstrations containing the requisite logical operator composition for the NL2SQL task on hand, thereby guiding LLMs to produce better SQL translation. PURPLE achieves a new state-of-the-art performance of 80.5% exact-set match accuracy and 87.8% execution match accuracy on the validation set of the popular NL2SQL benchmark Spider. PURPLE maintains high accuracy across diverse benchmarks, budgetary constraints, and various LLMs, showing robustness and cost-effectiveness.

Recent advancements in TableQA leverage sequence-to-sequence (Seq2seq) deep learning models to accurately respond to natural language queries. These models achieve this by converting the queries into SQL queries, using information drawn from one or more tables. However, Seq2seq models often produce uncertain (low-confidence) predictions when distributing probability mass across multiple outputs during a decoding step, frequently yielding translation errors. To tackle this problem, we present Ckif , a confidence-based knowledge integration framework that uses a two-stage deep-learning-based ranking technique to mitigate the low-confidence problem commonly associated with Seq2seq models for TableQA. The core idea of Ckif is to introduce a flexible framework that seamlessly integrates with any existing Seq2seq translation models to enhance their performance. Specifically, by inspecting the probability values in each decoding step, Ckif first masks out each low-confidence prediction from the predicted outcome of an underlying Seq2seq model. Subsequently, Ckif integrates prior knowledge of query language to generalize masked-out queries, enabling the generation of all possible queries and their corresponding NL expressions. Finally, a two-stage deep-learning ranking approach is developed to evaluate the semantic similarity of NL expressions to a given NL question, hence determining the best-matching result. Extensive experiments are conducted to investigate Ckif by applying it to five state-of-the-art Seq2seq models using a widely used public benchmark. The experimental results indicate that Ckif consistently enhances the performance of all the Seq2seq models, demonstrating its effectiveness for better supporting TableQA.