Controlling hallucinations at word level in data-to-text generation
Open accessThe DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.
Abstract
Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field has been recently boosted by the use of neural-based generators which exhibit on one side great syntactic skills without the need of hand-crafted pipelines; on the other side, the quality of the generated text reflects the quality of the training data, which in realistic settings only offer imperfectly aligned structure-text pairs. Consequently, state-of-art neural models include misleading statements –usually called hallucinations—in their outputs. The control of this phenomenon is today a major challenge for DTG, and is the problem addressed in the paper. Previous work deal with this issue at the instance level: using an alignment score for each table-reference pair. In contrast, we propose a finer-grained approach, arguing that hallucinations should rather be treated at the word level. Specifically, we propose a Multi-Branch Decoder which is able to leverage word-level labels to learn the relevant parts of each training instance. These labels are obtained following a simple and efficient scoring procedure based on co-occurrence analysis and dependency parsing. Extensive evaluations, via automated metrics and human judgment on the standard WikiBio benchmark, show the accuracy of our alignment labels and the effectiveness of the proposed Multi-Branch Decoder. Our model is able to reduce and control hallucinations, while keeping fluency and coherence in generated texts. Further experiments on a degraded version of ToTTo show that our model could be successfully used on very noisy settings.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Instance-level scores can lead to a signal loss because divergences occur at the word level; i.e., parts of the target sentence are loyal to the source input, while others diverge [216].”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [216]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Therefore, all types of decoder can be used, such as Recurrent Neural Networks (RNNs) [57], Transformers [67], and Convolu-tional Neural Networks [16].”
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“Training is performed using the Adam algorithm (Kingma and Ba 2015) with learning rate η = 10−3, β1 = 0.”
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 1×
“2019) to fine-tune a BERT model (Devlin et al. 2019) on the UD English ParTUT dataset (Sanguinetti and Bosco 2015); Stanza (Qi et al.”
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 1×
“2019) to fine-tune a BERT model (Devlin et al. 2019) on the UD English ParTUT dataset (Sanguinetti and Bosco 2015); Stanza (Qi et al.”
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · cited 1×
“We use the general attention mechanism with input feeding (Luong et al. 2015) and the same copy mechanism as See et al.”
Get To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775
Research works printed but not linked: 4
- Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: ICLR
- Ferreira TC, van der Lee C, van Miltenburg E, Krahmer E (2019) Neural data-to-text generation: A comparison between pipeline and end-to-end architectures. In: EMNLP-IJCNLP
- Perez-Beltrachini L, Lapata M (2018) Bootstrapping generators from noisy data. In: NAACL-HLT · DOI
- Puduppully R, Dong L, Lapata M (2019b) Data-to-text generation with entity modeling. In: ACL · DOI · Paper page
Cited by
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
“, parts of the target sentence are loyal to the source input, while others diverge [110].”
BackgroundInfluentialSiren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., et al. (2025) · Computational Linguistics · doi:10.1162/coli.a.16 · Cited by 534
“Examples include the multi-branch decoder (Rebuffel et al., 2022) and the uncertainty-aware decoder (Xiao and Wang, 2021).”
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Liu, F., Liu, Y., Shi, L., Yang, Z., Zhang, L., Lian, X., Li, Z., & Ma, Y. (2024) · arXiv · doi:10.48550/arxiv.2404.00971 · Cited by 188
“…advanced training techniques ( e.g. reinforcement learning [56]), improved decoding strategies [10], [38], model architecture optimization [42], [60], and multi-agent interaction [14], as well as leveraging external tools for knowledge retrieval and fact-checking [75], [78], are also worthwhile…”
Wang, Y., Pan, Y., Su, Z., Deng, Y., Zhao, Q., Du, L., Luan, T. H., Kang, J., & Niyato, D. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576176 · Cited by 68
“Multi-branch decoder [208] and uncertainty-aware decoder [209] are two examples of modified decoder structures to mitigate hallucinations.”
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
Liu, T., Zhang, Y., Brockett, C., Mao, Y., Sui, Z., Chen, W., & Dolan, B. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.464 · Cited by 63
Metadata
- Authors
- Rebuffel, C., Roberti, M., Soulier, L., Scoutheeten, G., Cancelliere, R., & Gallinari, P.
- Affiliations
- University of Turin (IT)
- Centre National de la Recherche Scientifique (FR)
- BNP Paribas (France) (FR)
- Corresponding author
- Roberti, Marco
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2021-10-22
- Volume
- 36
- Issue
- 1
- Pages
- 318-354
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W3127986942
- Semantic Scholar
- 0368a16887369a56d9abb41ae8d697d4691a2021
- Cited by
- 50
- References
- 77
- Citations by year
- 2026: 5 · 2025: 14 · 2024: 4 · 2023: 15 · 2022: 9 · 2021: 3
- FWCI
- 2.71
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Data Mining and Knowledge Discovery (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Institutional Research Information System University of Turin (University of Turin) (submittedVersion, cc-by)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Funders
- Horizon2020 AI4EU (825619)
- ANR JCJC SESAMS (ANR-18-CE23-0001)
- Istituto Nazionale di Alta Matematica “Francesco Severi”
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- data-to-text generation, hallucination mitigation, co-occurrence analysis, dependency parsing, noisy training data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Controlling hallucinations at word level in data-to-text generation. https://app.cochat.ai/papers/10.1007/s10618-021-00801-4
- The paper
- Rebuffel, C., Roberti, M., Soulier, L., Scoutheeten, G., Cancelliere, R., & Gallinari, P. (2022). Controlling hallucinations at word level in data-to-text generation. Data Mining and Knowledge Discovery. https://doi.org/10.1007/s10618-021-00801-4
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.