CPIL is a contrastive two-stage method that enforces paraphrase invariance on limited labeled data to outperform baselines in hallucination detection across 11 tasks.
Supervised contrastive learning for pre-trained language model fine-tuning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.
A router mixes supervised and reward fine-tuning with compiler/security feedback so small code LLMs produce more functionally correct and security-cleared vulnerability patches on three repair benchmarks.
Supervised contrastive learning as an auxiliary loss during CTC fine-tuning improves accent robustness in ASR, yielding up to 29% relative WER reduction on unseen accents.
LLMSniffer improves detection of LLM-generated code on GPTSniffer and Whodunit benchmarks by fine-tuning GraphCodeBERT via two-stage supervised contrastive learning plus preprocessing and MLP classification.
citing papers explorer
-
Cross Paraphrastic Invariance Learning for Hallucination Detection
CPIL is a contrastive two-stage method that enforces paraphrase invariance on limited labeled data to outperform baselines in hallucination detection across 11 tasks.
-
G-Loss: Graph-Guided Fine-Tuning of Language Models
G-Loss builds a document-similarity graph and uses semi-supervised label propagation to guide fine-tuning of language models, yielding higher accuracy than standard losses on five classification benchmarks.
-
SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
A router mixes supervised and reward fine-tuning with compiler/security feedback so small code LLMs produce more functionally correct and security-cleared vulnerability patches on three repair benchmarks.
-
Contrastive Regularization for Accent-Robust ASR
Supervised contrastive learning as an auxiliary loss during CTC fine-tuning improves accent robustness in ASR, yielding up to 29% relative WER reduction on unseen accents.
-
LLMSniffer: Detecting LLM-Generated Code via GraphCodeBERT and Supervised Contrastive Learning
LLMSniffer improves detection of LLM-generated code on GPTSniffer and Whodunit benchmarks by fine-tuning GraphCodeBERT via two-stage supervised contrastive learning plus preprocessing and MLP classification.