Papers › Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference

Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference

8 Oct 2020EMNLP 2020 11arXiv:2010.03760archive 2025-07-28

Xiaoan Ding, Tianyu Liu, Baobao Chang, Zhifang Sui, Kevin Gimpel

While discriminative neural network classifiers are generally preferred, recent work has shown advantages of generative classifiers in term of data efficiency and robustness. In this paper, we focus on natural language inference (NLI). We propose GenNLI, a generative classifier for NLI tasks, and empirically characterize its performance by comparing it to five baselines, including discriminative models and large-scale pretrained language representation models like BERT. We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work . In particular, we find strong results with a simple unbounded modification to log loss, which we call the "infinilog loss". Our experiments show that GenNLI outperforms both discriminative and pretrained baselines across several challenging NLI experimental settings, including small training sets, imbalanced label distributions, and label noise.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tyliupku/gen-nli officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDiscriminative Fine-TuningDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections