# Selective Generation for Controllable Language Models

arXiv: https://arxiv.org/abs/2307.09254 · HTML: https://mlsanity.com/paper/2307.09254/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 18 Jul 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Adaptive Conformal Inference Under Distribution Shift](https://mlsanity.com/paper/2106.00170/) (2021)
- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [Calibrating Sequence likelihood Improves Conditional Language Generation](https://mlsanity.com/paper/2210.00045/) (2022)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://mlsanity.com/paper/1809.02922/) (2018)
- [Selection by Prediction with Conformal p-values](https://mlsanity.com/paper/2210.01408/) (2022)
- [PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction](https://mlsanity.com/paper/2001.00106/) (2019)
- [Few-shot Conformal Prediction with Auxiliary Tasks](https://mlsanity.com/paper/2102.08898/) (2021)
- [Can NLI Models Verify QA Systems' Predictions?](https://mlsanity.com/paper/2104.08731/) (2021)
- [PAC Prediction Sets Under Covariate Shift](https://mlsanity.com/paper/2106.09848/) (2021)
- [Learning to Reject with a Fixed Predictor: Application to Decontextualization](https://mlsanity.com/paper/2301.09044/) (2023)
- [PAC Prediction Sets for Meta-Learning](https://mlsanity.com/paper/2207.02440/) (2022)

## Built on by (most cited first, 15 of 15)

- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels](https://mlsanity.com/paper/2502.14268/) (2025)
- [Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization](https://mlsanity.com/paper/2604.17984/) (2026)
- [When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation](https://mlsanity.com/paper/2606.29054/) (2026)
- [Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents](https://mlsanity.com/paper/2604.27283/) (2026)
- [Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2505.11731/) (2025)
- [Towards Functional Correctness of Large Code Models with Selective Generation](https://mlsanity.com/paper/2505.13553/) (2025)
- [Capability Self-Assessment in Large Language Models](https://mlsanity.com/paper/2606.00251/) (2026)
- [SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications](https://mlsanity.com/paper/2608.05439/) (2026)
- [BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection](https://mlsanity.com/paper/2604.10389/) (2026)
- [Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems](https://mlsanity.com/paper/2609.05928/) (2026)
- [Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models](https://mlsanity.com/paper/2609.22243/) (2026)
- [Pinocchio: Fast Uncertainty Estimates for Black-Box Language Models](https://mlsanity.com/paper/2609.24881/) (2026)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)

## Abstract (arXiv)

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to mitigating the hallucination problem in various supervised downstream tasks. However, the lack of appropriate correctness metric hinders applying such principled methods to language generation tasks. In this paper, we circumvent this problem by leveraging the concept of textual entailment to evaluate the correctness of the generated sequence, and propose two selective generation algorithms which control the false discovery rate with respect to the textual entailment relation (FDR-E) with a theoretical guarantee: textttSGen^textttSup and textttSGen^textttSemi. textttSGen^textttSup, a direct modification of the selective prediction, is a supervised learning algorithm which exploits entailment-labeled data, annotated by humans. Since human annotation is costly, we further propose a semi-supervised version, textttSGen^textttSemi, which fully utilizes the unlabeled data by pseudo-labeling, leveraging an entailment set function learned via conformal prediction. Furthermore, textttSGen^textttSemi enables to use more general class of selection functions, neuro-selection functions, and provides users with an optimal selection function class given multiple candidates. Finally, we demonstrate the efficacy of the textttSGen family in achieving a desired FDR-E level with comparable selection efficiency to those from baselines on both open and closed source GLMs. Code and datasets are provided at https://github.com/ml-postech/selective-generation.