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

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. 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). Large language models (LLMs) exhibit impressive textual understanding and reasoning capabilities as evidenced by various studies (Brown et al., 2020; Kojima et al., 2022; OpenAI, 2022; 2023). Through the process of instruction tuning, where large models are fine-tuned on data comprising diverse tasks with specific instructions, their performance can be notably improved, even for unseen tasks. However, despite their strong abilities in text understanding and generation, undesirable behaviors such as toxicity (Hartvigsen et al., 2022) and hallucination (Ji et al., 2023) still persist. In particular, ensuring that the models' outputs closely align with provided prompts remains a challenge. Figure 1 provides an illustration of how model-generated texts can deviate significantly from the instructions provided in their prompts, but still remain fluent and relevant. Figure 1: An illustration of the proposed approach utilizing future constraint satisfaction to guide generation. In this example, although "summer" is a more likely next token, generating it will lead to a lower score in the future constraint, which includes the keyword "snow".