@@ -121,6 +121,8 @@ All the related results are shown in `./results/nl_exec/{dataset_name}_{LLM_name
121121
122122### 3. Dataset Refine and Model Accuracy Evaluation
123123
124+ See ` dataset_refine.py ` for dataset error detection and fixing functionality.
125+
124126#### 3.1 Dataset Refine
125127Run the following command to *** detect and fix*** errors in the datasets.
126128``` shell
@@ -163,7 +165,27 @@ The results are shown in `./results/issues/{dataset_name}_train/`:
163165
164166#### 3.2 Model Accuracy Evaluation
165167
166- ** Working in progress and will be released soon :-)**
167-
168-
169- [ // ] : # ( ## Reference )
168+ See ` model_accuracy_improvement.py ` for SQLDriller's accuracy improvement directly on model inference.
169+
170+ ** Automatic shell scripts will come out soon.**
171+
172+
173+ ## Reference
174+ ```
175+ @article{10.1145/3725271,
176+ author = {Yang, Yicun and Wang, Zhaoguo and Xia, Yu and Wei, Zhuoran and Ding, Haoran and Piskac, Ruzica and Chen, Haibo and Li, Jinyang},
177+ title = {Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency},
178+ year = {2025},
179+ issue_date = {June 2025},
180+ publisher = {Association for Computing Machinery},
181+ address = {New York, NY, USA},
182+ volume = {3},
183+ number = {3},
184+ url = {https://doi.org/10.1145/3725271},
185+ doi = {10.1145/3725271},
186+ journal = {Proc. ACM Manag. Data},
187+ month = jun,
188+ articleno = {134},
189+ numpages = {28},
190+ keywords = {SQL query equivalence, execution consistency, language model, natural language interface for databases, text-to-SQL}
191+ }
0 commit comments