Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO
Current Text-to-SQL methods are evaluated and only focused on executable queries, overlooking the semantic alignment challenge -- both in terms of the semantic meaning of the query and the correctness of the execution results. Even execution accuracy itself shows significant drops when moving from English to other languages, with an average decline of 6 percentage points across non-English languages. We address these challenges by presenting a new framework that combines Group Relative Policy Optimization (GRPO) within a multilingual contrastive reward signal to enhance both task efficiency and semantic accuracy in Text-to-SQL systems in cross-lingual scenarios. Our method teaches models to obtain better correspondence between SQL generation and user intent by combining a reward signal based on semantic similarity. On the seven-language MultiSpider dataset, fine-tuning the LLaMA-3-3B model with GRPO improved the execution accuracy up to 87.4 percent (+26 pp over zero-shot) and semantic accuracy up to 52.29 percent (+32.86 pp). Adding our contrastive reward signal in the GRPO framework further improved the average semantic accuracy to 59.14 percent (+6.85 pp, up to +10 pp for Vietnamese). Our experiments showcase that a smaller, parameter-efficient 3B LLaMA model fine-tuned with our contrastive reward signal outperforms a much larger zero-shot 8B LLaMA model, with an uplift of 7.43 pp in execution accuracy (from 81.43 percent on the 8B model to 88.86 percent on the 3B model), and nearly matches its semantic accuracy (59.14 percent vs. 68.57 percent) -- all using just 3,000 reinforcement learning training examples. These results demonstrate how we can improve the performance of Text-to-SQL systems with contrastive rewards for directed semantic alignment, without requiring large-scale training datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSemantic SimilaritySimilar Papers 제목 키워드 기반
Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval
Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative…
Contrastive LearningOpen-Domain Question AnsweringRetrievalSemantic Similarity+2Bridging Language Gaps: Enhancing Few-Shot Language Adaptation
The disparity in language resources poses a challenge in multilingual NLP, with high-resource languages benefiting from extensive data, while low-resource languages lack sufficient data for effective training. Our Contra…
Natural Language UnderstandingNatural Language InferenceCross-Lingual TransferContrastive LearningEASE: Entity-Aware Contrastive Learning of Sentence Embedding
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown t…
ClusteringContrastive LearningSemantic Textual SimilaritySentence+6Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning
Recent works of music representation learning mainly focus on learning acoustic music representations with unlabeled audios or further attempt to acquire multi-modal music representations with scarce annotated audio-text…
Collaborative FilteringContrastive LearningMusic RecommendationRepresentation LearningEASE: Entity-Aware Contrastive Learning of Sentence Embedding
We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities.The advantage of using entity supervision is twofold: (1) entities have been shown to…
ClusteringContrastive LearningSemantic Textual SimilaritySentence+6