CoChat

Reducing Non-Normative Text Generation from Language Models

Open access
Peng, Xiangyu, Li, Siyan, Frazier, Spencer, Riedl, Mark · 2020 · Proceedings of the 13th International Conference on Natural Language Generation
Cited by 20

The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.

Abstract

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet.Consequently, they are prone to generating non-normative text (i.e. in violation of social norms).We introduce a technique for fine-tuning GPT-2, using a policy gradient reinforcement learning technique and a normative text classifier to produce reward and punishment values.We evaluate our technique on five data sets using automated and human participant experiments.The normative text classifier is 81-90% accurate when compared to gold-standard human judgements of normative and non-normative generated text.Our normative fine-tuning technique is able to reduce non-normative text by 27-61%, depending on the data set.

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 · 10.18653/v1/2020.inlg-1.43

Cites

17 of 17 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

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 17 references

Cited by

See all 20

Metadata

Authors
Peng, X., Li, S., Frazier, S., & Riedl, M.
Venue
Proceedings of the 13th International Conference on Natural Language Generation
Published
2020
Pages
374-383
OpenAlex
W3094997972
Cited by
20
References
17
FWCI
1.61
Type
conference paper
Language
en
Open access
hybrid

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: Reducing Non-Normative Text Generation from Language Models. https://app.cochat.ai/papers/10.18653/v1/2020.inlg-1.43
The paper
Peng, X., Li, S., Frazier, S., & Riedl, M. (2020). Reducing Non-Normative Text Generation from Language Models. Proceedings of the 13th International Conference on Natural Language Generation. https://doi.org/10.18653/v1/2020.inlg-1.43

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.