Pith. sign in

REVIEW 2 cited by

Language GANs Falling Short

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1811.02549 v6 pith:3IBMD26N submitted 2018-11-06 cs.CL cs.LG

classification cs.CLcs.LG
keywords biasdiversityexposuremodelsqualityadversarialeasierevaluation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Likelihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines, where poor performance is attributed to exposure bias (Bengio et al., 2015; Ranzato et al., 2015); at inference time, the model is fed its own prediction instead of a ground-truth token, which can lead to accumulating errors and poor samples. This line of reasoning has led to an outbreak of adversarial based approaches for NLG, on the account that GANs do not suffer from exposure bias. In this work, we make several surprising observations which contradict common beliefs. First, we revisit the canonical evaluation framework for NLG, and point out fundamental flaws with quality-only evaluation: we show that one can outperform such metrics using a simple, well-known temperature parameter to artificially reduce the entropy of the model's conditional distributions. Second, we leverage the control over the quality / diversity trade-off given by this parameter to evaluate models over the whole quality-diversity spectrum and find MLE models constantly outperform the proposed GAN variants over the whole quality-diversity space. Our results have several implications: 1) The impact of exposure bias on sample quality is less severe than previously thought, 2) temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Code to reproduce the experiments is available at github.com/pclucas14/GansFallingShort

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Moderately diverse LLM-generated data can improve fine-tuned model performance in low-data settings when distribution shift is minimal, while high diversity or large distribution shift hurts.

  2. Exploring the Impact of Temperature on Large Language Models:Hot or Cold?

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Temperature has skill-specific effects on LLM performance, and a trained prompt classifier can choose better per-prompt temperatures for small and medium models on some SuperGLUE tasks.

Pith tools