Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models

• URL: http://arxiv.org/abs/2608.25761v1
• Date: Wed, 26 Aug 2026 13:07:06 GMT
• Title: Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models
• Abstract summary: A common trade-off in large language models involves reducing the size of the model while increasing the amount of computation at inference time.<n>We show that the constrained trade-off behaves differently from the unconstrained trade-off.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: One common trade-off in the use of large language models involves reducing the size of the model while increasing the amount of computation at inference time, for example by using a wider beam search. In this paper, we examine the constrained case of this "model size vs. inference compute" trade-off, in which the model outputs are constrained by a strict grammar at inference time. Our results demonstrate that the constrained trade-off behaves differently from the unconstrained trade-off. We investigate the task of converting a prose query into an equivalent SQL query (text-to-SQL). Performance is evaluated on the Spider text-to-SQL benchmark, using the Qwen2.5-Instruct model family ranging in size from 0.5B to 7B parameters, all at 4-bit precision. We experiment with two approaches to varying inference compute: (i) beam search with a variable number of beams; and (ii) sample+vote, i.e., sampling several constrained outputs and then voting on their execution results, where the number of samples is varied. On the 1034-example development set, we find that: (a) both beam search and sample+vote improve accuracy, especially on smaller model sizes; (b) the "model size vs.\ inference compute" trade-off is not advantageous in this experiment, because moving to a larger model size typically results in higher accuracy than increasing inference compute on the same model size; (c) beam search outperforms sample+vote at a matched inference budget. This latter result is of particular interest since it contrasts with the findings of the unconstrained trade-off.

Related papers

• More Accurate or More Efficient? Evaluating Locally Deployed Compact Open-Weight Language Models for Mathematical Reasoning [0.0]
  This paper presents a controlled, documented procedure for evaluating locally hosted LLMs on mathematical reasoning.<n>It combines fixed inference settings, hierarchical answer extraction and verification, explicit failure-mode classification, and per-question resource measurement.<n>Preliminary findings indicate that accuracy alone is an insufficient basis for selecting a local model.
  arXiv  Detail & Related papers  (2026-08-22T17:24:28Z)
• Model Equality Testing: Which Model Is This API Serving? [59.005869726179455]
  API providers may quantize, watermark, or finetune the underlying model, changing the output distribution.<n>We formalize detecting such distortions by Model Equality Testing, a two-sample testing problem.<n>A test built on a simple string kernel achieves a median of 77.4% power against a range of distortions.
  arXiv  Detail & Related papers  (2024-10-26T18:34:53Z)
• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling [81.34900892130929]
  We explore inference compute as another axis for scaling, using the simple technique of repeatedly sampling candidate solutions from a model.<n>Across multiple tasks and models, we observe that coverage scales with the number of samples over four orders of magnitude.<n>In domains like coding and formal proofs, where answers can be automatically verified, these increases in coverage directly translate into improved performance.
  arXiv  Detail & Related papers  (2024-07-31T17:57:25Z)
• Single-Stage Visual Relationship Learning using Conditional Queries [60.90880759475021]
  TraCQ is a new formulation for scene graph generation that avoids the multi-task learning problem and the entity pair distribution. We employ a DETR-based encoder-decoder conditional queries to significantly reduce the entity label space as well. Experimental results show that TraCQ not only outperforms existing single-stage scene graph generation methods, it also beats many state-of-the-art two-stage methods on the Visual Genome dataset.
  arXiv  Detail & Related papers  (2023-06-09T06:02:01Z)
• Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models [65.52639709094963]
  Methods such as beam search and Gumbel top-k sampling can guarantee a different output for each element of the beam, but are not easy to parallelize. We present a framework for sampling according to an arithmetic code book implicitly defined by a large language model.
  arXiv  Detail & Related papers  (2022-10-18T22:19:41Z)
• Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference [10.536415845097661]
  We propose a method for predicting the performance of NLI models without fine-tuning them. We show that the accuracy of the cosine similarity approach correlates strongly with the accuracy of the classification approach with a Pearson correlation coefficient of 0.65. Our method can lead to significant time savings in the process of model selection.
  arXiv  Detail & Related papers  (2022-02-21T18:10:24Z)
• Significance tests of feature relevance for a blackbox learner [6.72450543613463]
  We derive two consistent tests for the feature relevance of a blackbox learner. The first evaluates a loss difference with perturbation on an inference sample. The second splits the inference sample into two but does not require data perturbation.
  arXiv  Detail & Related papers  (2021-03-02T00:59:19Z)
• Approximating a Target Distribution using Weight Queries [25.392248158616862]
  We propose an interactive algorithm that iteratively selects data set examples and performs corresponding weight queries. We derive an approximation bound on the total variation distance between the reweighting found by the algorithm and the best achievable reweighting.
  arXiv  Detail & Related papers  (2020-06-24T11:17:43Z)
• The Right Tool for the Job: Matching Model and Instance Complexities [62.95183777679024]
  As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. We propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks.
  arXiv  Detail & Related papers  (2020-04-16T04:28:08Z)
• Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages [112.65994041398481]
  We propose a Bayesian generative model for the space of neural parameters. We infer the posteriors over such latent variables based on data from seen task-language combinations. Our model yields comparable or better results than state-of-the-art, zero-shot cross-lingual transfer methods.
  arXiv  Detail & Related papers  (2020-01-30T16:58:56Z)

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.