CoChat

Controlling hallucinations at word level in data-to-text generation

Open access
Rebuffel, Clement, Roberti, Marco, Soulier, Laure, Scoutheeten, Geoffrey, Cancelliere, Rossella, Gallinari, Patrick · 2022 · Data Mining and Knowledge Discovery

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s10618-021-00801-4

Cites

78 of 78 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 78 references

Research works printed but not linked: 4

  1. Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: ICLR
  2. 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
  3. Perez-Beltrachini L, Lapata M (2018) Bootstrapping generators from noisy data. In: NAACL-HLT · DOI
  4. Puduppully R, Dong L, Lapata M (2019b) Data-to-text generation with entity modeling. In: ACL · DOI · Paper page

Cited by

See all 53

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
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
Licence
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.