CCHD formulates hallucination detector training as constrained optimization with paraphrase-consistency and label-preservation rules solved via gradient descent-ascent, outperforming baselines on factuality benchmarks.
Factcg: Enhancing fact checkers with graph-based multi-hop data,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CPIL is a contrastive two-stage method that enforces paraphrase invariance on limited labeled data to outperform baselines in hallucination detection across 11 tasks.
citing papers explorer
-
Constrained Paraphrase Consistency for LLM Hallucination Detection
CCHD formulates hallucination detector training as constrained optimization with paraphrase-consistency and label-preservation rules solved via gradient descent-ascent, outperforming baselines on factuality benchmarks.
-
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.