Text-to-SQL technology converts natural language queries into SQL statements for database retrieval. Recent advances in large language models (LLMs) have improved Text-to-SQL performance, but generated SQL often contains semantic or syntax errors that degrade user experience and system stability. Existing SQL error detection methods are costly, lack interpretability, and do not support error labeling. To overcome these issues, we propose SQL-Checker a specialized model for Text-to-SQL error detection. We first analyze common error factors in Text-to-SQL, and we design a novel data synthesis framework based on these error factors. This framework simulates error factors to construct a basic error SQL data, and then using an error analysis template to distill high-quality SQL error analysis data from large-scale models. For complex errors, a self-guided iterative distillation strategy further enhances data quality. SQL-Checker is then trained on this distilled dataset. Additionally, we refine SQL error labeling and, integrate error label recognition into the detection task, enabling macro-level cause analysis. Experiments show SQL-Checker achieves state-of-the-art results on multiple error detection datasets. Incorporating SQL-Checker into the Text-to-SQL pipeline also improves execution accuracy.

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised CoT methods primarily select examples based on the semantics of the questions, which can introduce noise and lack interpretability. In this paper, we propose leveraging reasoning patterns to enhance CoT prompting effectiveness. Reasoning patterns represent the process by which language models arrive at their final results. By utilizing prior knowledge and prompt-based methods from large models, we first construct task-specific pattern sets. We then select diverse demonstrations based on different reasoning patterns. This approach not only mitigates the impact of noise but also provides explicit interpretability to help us understand the mechanisms of CoT. Extensive experiments demonstrate that our method is more robust and consistently leads to improvements across various reasoning tasks.

Text-to-SQL is a subtask in semantic parsing that has seen rapid progress with the evolution of Large Language Models (LLMs). However, LLMs face challenges due to hallucination issues and a lack of domain-specific database knowledge(such as table schema and cell values). As a result, they can make errors in generating table names, columns, and matching values to the correct columns in SQL statements. This paper introduces a method of knowledge injection to enhance LLMs’ ability to understand schema contents by incorporating prior knowledge. This approach improves their performance in Text-to-SQL tasks. Experimental results show that pre-training LLMs on domain-specific database knowledge and fine-tuning them on downstream Text-to-SQL tasks significantly improves the Execution Match (EX) and Exact Match (EM) metrics across various models. This effectively reduces errors in generating column names and matching values to the columns. Furthermore, the knowledge-injected models can be applied to many downstream Text-to-SQL tasks, demonstrating the generalizability of the approach presented in this paper.

Xuepeng Wang, Li Zhao, Bing Liu, Tao Chen, Feng Zhang, Di Wang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Incorporating temporal information into recommender systems has recently attracted increasing attention from both the industrial and academic research communities. Existing methods mostly reduce the temporal information of behaviors to behavior sequences for subsequently RNN-based modeling. In such a simple manner, crucial time-related signals have been largely neglected. This paper aims to systematically investigate the effects of the temporal information in sequential recommendations. In particular, we firstly discover two elementary temporal patterns of user behaviors: "absolute time patterns'' and "relative time patterns'', where the former highlights user time-sensitive behaviors, e.g., people may frequently interact with specific products at certain time point, and the latter indicates how time interval influences the relationship between two actions. For seamlessly incorporating these information into a unified model, we devise a neural architecture that jointly learns those temporal patterns to model user dynamic preferences. Extensive experiments on real-world datasets demonstrate the superiority of our model, comparing with the state-of-the-arts.

Junjie Li, Xuepeng Wang, Dawei Yin, Chengqing Zong. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Solving the cold-start problem in review spam detection is an urgent and significant task.It can help the on-line review websites to relieve the damage of spammers in time, but has never been investigated by previous work.This paper proposes a novel neural network model to detect review spam for the cold-start problem, by learning to represent the new reviewers' review with jointly embedded textual and behavioral information.Experimental results prove the proposed model achieves an effective performance and possesses preferable domain-adaptability.It is also applicable to a large-scale dataset in an unsupervised way.

Review spam detection is a key task in opinion mining.To accomplish this type of detection, previous work has focused mainly on effectively representing fake and non-fake reviews with discriminative features, which are discovered or elaborately designed by experts or developers.This paper proposes a novel review spam detection method that learns the representation of reviews automatically instead of heavily relying on experts' knowledge in a data-driven manner.More specifically, according to 11 relations (generated automatically from two basic patterns) between reviewers and products, we employ tensor decomposition to learn the embeddings of the reviewers and products in a vector space.We collect relations between any two entities (reviewers and products), which results in much useful and global information.We concatenate the review text, the embeddings of the reviewer and the reviewed product as the representation of a review.Based on such representations, the classifier could identify the opinion spam more precisely.Experimental results on an open Yelp dataset show that our method could effectively enhance the spam detection accuracy compared with the stateof-the-art methods.

In this study, the authors present a low‐complexity iterative joint detection–decoding algorithm for majority‐logic decodable non‐binary low‐density parity‐check (LDPC) coded modulation systems. In the proposed algorithm, a hard‐in–hard‐out decoder is combined with a hard‐decision signal detector in an iterative manner. Each iteration consists of five phases. Firstly, the detector makes hard decisions based on the iteratively updated ‘received’ signals; secondly, these hard decisions are distributed via variable nodes to check nodes; thirdly, check nodes compute hard extrinsic messages; fourthly, each variable node counts hard extrinsic messages from its adjacent check nodes and feeds back to the detection node the symbol with the most votes as well as the difference between the most votes and the second most votes; finally, these feedbacks are used to shift each ‘received’ signal point along an estimated direction to possibly reduce noise. The proposed algorithm requires only integer operations and finite field operations and consequently can be implemented with simple combinational logic circuits in practical systems. Simulation results show that the proposed algorithm performs well and hence serves as an attractive candidate for trading off performance against complexity for majority‐logic decodable non‐binary LDPC codes.

In this paper, we present a low-complexity joint detection-decoding algorithm for nonbinary LDPC coded-modulation systems. The algorithm combines hard-decision decoding using the message-passing strategy with the signal detector in an iterative manner. It requires low computational complexity, offers good system performance and has a fast rate of decoding convergence. Compared to the q-ary sum-product algorithm (QSPA), it provides an attractive candidate for practical applications of q-ary LDPC codes.