Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models

Chenxu Yang; Qingyi Si; Lanrui Wang; Zheng Lin

AAAI 2026technical0 citations

Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models

Chenxu Yang, Qingyi Si, Lanrui Wang, Zheng Lin

Abstract

Grounding responses in external knowledge represents an effective strategy for mitigating hallucinations in Large Language Models (LLMs). However, current LLMs struggle to seamlessly integrate knowledge while simultaneously maintaining faithfulness (or fidelity) and expressiveness, capabilities that humans naturally possess. This limitation results in outputs that either lack support from external knowledge, thereby compromising faithfulness, or appear overly verbose and unnatural, thus sacrificing expressiveness. In this work, to break the trade-off between faithfulness and expressiveness, we propose Collaborative Decoding (CoDe), a novel approach that dynamically integrates output probabilities generated with and without external knowledge. This integration is guided by distribution divergence and model confidence, enabling the selective activation of relevant and reliable expressions from the model

BibTeX

@inproceedings{aaai2026_breakingthetrade,
  title = {Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models},
  author = {Chenxu Yang and Qingyi Si and Lanrui Wang and Zheng Lin},
  booktitle = {AAAI 2026},
  year = {2026}
}