paper-with-me

Papers

Rationalization Models for Text-to-SQL

2025-02-10 · Gaetano Rossiello, Nhan Pham, Michael Glass, JunKyu Lee, Dharmashankar Subramanian

We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and explanations, serving as incremental steps toward constructing the final SQL query. The process begins with manually annotating a small set of examples, which are then used to prompt a large language model in an iterative, dynamic few-shot knowledge distillation procedure from a teacher model. A rationalization model is subsequently trained on the validated decomposed queries, enabling extensive synthetic CoT annotations for text-to-SQL datasets. To evaluate the approach, we fine-tune small language models with and without these rationales on the BIRD dataset. Results indicate that step-by-step query generation improves execution accuracy, especially for moderately and highly complex queries, while also enhancing explainability.

📄 PDF Abstract BibTeX arXiv:2502.06759

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language ModelText to SQLText-To-SQL

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Interlock-Free Multi-Aspect Rationalization for Text Classification

2022-05-13 · Shuangqi Li, Diego Antognini, Boi Faltings

Explanation is important for text classification tasks. One prevalent type of explanation is rationales, which are text snippets of input text that suffice to yield the prediction and are meaningful to humans. A lot of r…

Classificationtext-classificationText Classification

Towards Trustworthy Explanation: On Causal Rationalization

2023-06-25 · Wenbo Zhang, Tong Wu, Yunlong Wang, Yong Cai 외

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in pr…

Causal Inference

Rationalization for Explainable NLP: A Survey

2023-01-21 · Sai Gurrapu, Ajay Kulkarni, Lifu Huang, Ismini Lourentzou 외

Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expe…

Explainable Artificial Intelligence (XAI)Question AnsweringSurveytext-classification+2

Few-Shot Self-Rationalization with Natural Language Prompts

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a…

Few-Shot Self-Rationalization with Natural Language Prompts

2021-11-16 · Findings (NAACL) 2022 7 · Ana Marasović, Iz Beltagy, Doug Downey, Matthew E. Peters

Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a…