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

Lifu Tu, Semih Yavuz, qu jin, Jiacheng Xu, Rui Meng, Caiming Xiong, Yingbo Zhou

Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models: 3 upvotes on Hugging Face Daily Papers, #13 of 14 papers on 2023-12-12. Day-by-day upvote history.

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).

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.