Collaborative Decoding fuses a knowledge-conditioned and a context-only token distribution with confidence- and divergence-based weights plus knowledge-aware reranking, improving faithfulness while keeping expressiveness across six LLMs and three dialogue datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
Collaborative Decoding fuses a knowledge-conditioned and a context-only token distribution with confidence- and divergence-based weights plus knowledge-aware reranking, improving faithfulness while keeping expressiveness across six LLMs and three dialogue datasets.