# Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation

arXiv: https://arxiv.org/abs/1910.08684 · HTML: https://mlsanity.com/paper/1910.08684/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2019.

## Built on by (most cited first, 30 of 62)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection](https://mlsanity.com/paper/2409.17504/) (2024)
- [Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark](https://mlsanity.com/paper/2105.00071/) (2021)
- [Exposing Attention Glitches with Flip-Flop Language Modeling](https://mlsanity.com/paper/2306.00946/) (2023)
- [On the Calibration of Large Language Models and Alignment](https://mlsanity.com/paper/2311.13240/) (2023)
- [Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting](https://mlsanity.com/paper/2311.13314/) (2023)
- [Text Generation by Learning from Demonstrations](https://mlsanity.com/paper/2009.07839/) (2020)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder](https://mlsanity.com/paper/2304.04052/) (2023)
- [Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models](https://mlsanity.com/paper/2407.04121/) (2024)
- [SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation](https://mlsanity.com/paper/2305.13194/) (2023)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [AI Hallucinations: A Misnomer Worth Clarifying](https://mlsanity.com/paper/2401.06796/) (2024)
- [KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection](https://mlsanity.com/paper/2403.02253/) (2024)
- [Teaching Language Models to Hallucinate Less with Synthetic Tasks](https://mlsanity.com/paper/2310.06827/) (2023)
- [Focus Attention: Promoting Faithfulness and Diversity in Summarization](https://mlsanity.com/paper/2105.11921/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [On Diversified Preferences of Large Language Model Alignment](https://mlsanity.com/paper/2312.07401/) (2023)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)

## Abstract (arXiv)

We address the issue of hallucination in data-to-text generation, i.e., reducing the generation of text that is unsupported by the source. We conjecture that hallucination can be caused by an encoder-decoder model generating content phrases without attending to the source; so we propose a confidence score to ensure that the model attends to the source whenever necessary, as well as a variational Bayes training framework that can learn the score from data. Experiments on the WikiBio (Lebretet al., 2016) dataset show that our approach is more faithful to the source than existing state-of-the-art approaches, according to both PARENT score (Dhingra et al., 2019) and human evaluation. We also report strong results on the WebNLG (Gardent et al., 2017) dataset.