A frozen language model's log-likelihood gain from source conditioning, aggregated as SCDG, outperforms lexical, embedding, and prompted-LLM baselines for generative plagiarism detection and source reranking.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
A frozen language model's log-likelihood gain from source conditioning, aggregated as SCDG, outperforms lexical, embedding, and prompted-LLM baselines for generative plagiarism detection and source reranking.