# Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding

Source: [Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding](<https://www.sota2.com/research/paper/68fa75181e209131cea65baf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:26:16.510Z

Authors: Lifu Tu, Semih Yavuz, Jin Qu, Jiacheng Xu, Rui Meng, Caiming Xiong, Yingbo Zhou

Published: 2023-12-11T06:35:33.000Z

## Abstract

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired behaviors such as toxicity or hallucinations can manifest. While much larger models (e.g., ChatGPT) may demonstrate strength in mitigating these issues, there is still no guarantee of complete prevention. In this work, we propose formalizing text generation as a future-constrained generation problem to minimize undesirable behaviors and enforce faithfulness to instructions. The estimation of future constraint satisfaction, accomplished using LLMs, guides the text generation process. Our extensive experiments demonstrate the effectiveness of the proposed approach across three distinct text generation tasks: keyword-constrained generation (Lin et al., 2020), toxicity reduction (Gehman et al., 2020), and factual correctness in question-answering (Gao et al., 2023).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.06149>)

[PDF](<https://arxiv.org/pdf/2312.06149.pdf>)
