paper-with-me

홈 › Papers

Text-to-SQL Calibration: No Need to Ask -- Just Rescale Model Probabilities

2024-11-23 · Ashwin Ramachandran, Sunita Sarawagi

Calibration is crucial as large language models (LLMs) are increasingly deployed to convert natural language queries into SQL for commercial databases. In this work, we investigate calibration techniques for assigning confidence to generated SQL queries. We show that a straightforward baseline -- deriving confidence from the model's full-sequence probability -- outperforms recent methods that rely on follow-up prompts for self-checking and confidence verbalization. Our comprehensive evaluation, conducted across two widely-used Text-to-SQL benchmarks and multiple LLM architectures, provides valuable insights into the effectiveness of various calibration strategies.

📄 PDF Abstract BibTeX arXiv:2411.16742

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language QueriesText to SQLText-To-SQL

Similar Papers 제목 키워드 기반

Platt-Bin: Efficient Posterior Calibrated Training for NLP Classifiers

2022-05-01 · Findings (ACL) 2022 5 · Rishabh Singh, Shirin Goshtasbpour

Modern NLP classifiers are known to return uncalibrated estimations of class posteriors. Existing methods for posterior calibration rescale the predicted probabilities but often have an adverse impact on final classifica…

Classification

Posterior Calibrated Training on Sentence Classification Tasks

2020-04-29 · ACL 2020 6 · Taehee Jung, Dongyeop Kang, Hua Cheng, Lucas Mentch 외

Most classification models work by first predicting a posterior probability distribution over all classes and then selecting that class with the largest estimated probability. In many settings however, the quality of pos…

ClassificationGeneral ClassificationSentenceSentence Classification

Cut your Losses with Squentropy

2023-02-08 · Like Hui, Mikhail Belkin, Stephen Wright

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests t…

ClassificationMulti-class Classification

Improved Uncertainty Post-Calibration via Rank Preserving Transforms

2021-01-01 · Yu Bai, Tengyu Ma, Huan Wang, Caiming Xiong

Modern machine learning models with high accuracy often exhibit poor uncertainty calibration: the output probabilities of the model do not reflect its accuracy, and tend to be over-confident. Existing post-calibration me…

text-classificationText Classification

Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment

2026-05-06 · Seunghan Lee arxiv

TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift…