Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL

• URL: http://arxiv.org/abs/2510.13827v1
• Date: Fri, 10 Oct 2025 03:07:55 GMT
• Title: Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL
• Authors: Ashish Kattamuri, Ishita Prasad, Meetu Malhotra, Arpita Vats, Rahul Raja, Albert Lie,
• Abstract summary: Current Text-to-language methods only focus on executable queries, overlooking the semantic alignment challenge.<n>We present a new framework that combines a multilingual contrastive reward signal to enhance both task efficiency and semantic accuracy.<n>Our method teaches models to obtain better correspondence between generation and user intent by combining a reward signal based on semantic similarity.
• Score: 2.8727471514655902
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Evaluating NL2SQL via SQL2NL [45.88028371034407]
  New framework generates semantically equivalent, lexically diverse queries.<n>State-of-the-art models are far more brittle than standard benchmarks suggest.
  arXiv  Detail & Related papers  (2025-09-04T21:03:59Z)
• ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback [49.21833666405111]
  Large language models (LLMs) excel in many reasoning tasks, but their ability to leverage Chain-of-Thought (CoT) reasoning remains underexplored.<n>We propose ExCoT, a novel framework that iteratively optimize open-source LLMs by combining CoT reasoning with off-policy and on-policy DPO.
  arXiv  Detail & Related papers  (2025-03-25T18:17:36Z)
• Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference [0.0]
  We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference.<n>EAD switches between different-sized models based on prediction uncertainty.<n>We show remarkable efficiency gains across different model families.
  arXiv  Detail & Related papers  (2025-02-05T22:15:21Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• DataComp-LM: In search of the next generation of training sets for language models [200.5293181577585]
  DataComp for Language Models (DCLM) is a testbed for controlled dataset experiments with the goal of improving language models.<n>We provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations.<n>Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing at model scales ranging from 412M to 7B parameters.
  arXiv  Detail & Related papers  (2024-06-17T17:42:57Z)
• Progressive-Hint Prompting Improves Reasoning in Large Language Models [63.98629132836499]
  This paper proposes a new prompting method, named Progressive-Hint Prompting (PHP) It enables automatic multiple interactions between users and Large Language Models (LLMs) by using previously generated answers as hints to progressively guide toward the correct answers. We conducted extensive and comprehensive experiments on seven benchmarks. The results show that PHP significantly improves accuracy while remaining highly efficient.
  arXiv  Detail & Related papers  (2023-04-19T16:29:48Z)
• Self-Consistency Improves Chain of Thought Reasoning in Language Models [53.45015291520658]
  We explore a simple ensemble strategy, self-consistency, that significantly improves the reasoning accuracy of large language models. For arithmetic and commonsense reasoning benchmarks we find that self-consistency yields significant accuracy improvements.
  arXiv  Detail & Related papers  (2022-03-21T17:48:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.