# CAST: Achieving Stable LLM-based Text Analysis for Data Analytics

arXiv: https://arxiv.org/abs/2602.15861 · HTML: https://mlsanity.com/paper/2602.15861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 63 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages](https://mlsanity.com/paper/2204.08582/) (2022)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [Teaching Algorithmic Reasoning via In-context Learning](https://mlsanity.com/paper/2211.09066/) (2022)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators](https://mlsanity.com/paper/2406.13415/) (2024)
- [Training Chain-of-Thought via Latent-Variable Inference](https://mlsanity.com/paper/2312.02179/) (2023)
- [Towards Interpretable Natural Language Understanding with Explanations as Latent Variables](https://mlsanity.com/paper/2011.05268/) (2020)
- [ReConTab: Regularized Contrastive Representation Learning for Tabular Data](https://mlsanity.com/paper/2310.18541/) (2023)
- [StrucText-Eval: Evaluating Large Language Model's Reasoning Ability in Structure-Rich Text](https://mlsanity.com/paper/2406.10621/) (2024)
- [Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue](https://mlsanity.com/paper/2311.07445/) (2023)
- [SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds](https://mlsanity.com/paper/2508.18306/) (2025)
- [A framework for streamlined statistical prediction using topic models](https://mlsanity.com/paper/1904.06941/) (2019)

## Abstract (arXiv)

Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks is their inability to meet the high standards of output stability demanded by data analytics. To address this challenge, we introduce CAST (Consistency via Algorithmic Prompting and Stable Thinking), a framework that enhances output stability by constraining the model's latent reasoning path. CAST combines (i) Algorithmic Prompting to impose a procedural scaffold over valid reasoning transitions and (ii) Thinking-before-Speaking to enforce explicit intermediate commitments before final generation. To measure progress, we introduce CAST-S and CAST-T, stability metrics for bulleted summarization and tagging, and validate their alignment with human judgments. Experiments across publicly available benchmarks on multiple LLM backbones show that CAST consistently achieves the best stability among all baselines, improving Stability Score by up to 16.2%, while maintaining or improving output quality.