Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Junfeng Fang, Hongcheng Gao, Shiyu Ni, Xueqi Cheng

Keywords: Large Language Models, In-Context Faithfulness, Factuality Enhancement

Abstract:

As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context.
This requires LLMs to possess both context-faithfulness and factual accuracy.
While extensive efforts aim to reduce hallucinations through factuality enhancement methods, they also pose risks of hindering context-faithfulness, as factuality enhancement can lead LLMs to become overly confident in their parametric knowledge, causing them to overlook the relevant input context.
In this work, we argue that current factuality enhancement methods can significantly undermine the context-faithfulness of LLMs.
We first revisit the current factuality enhancement methods and evaluate their effectiveness in enhancing factual accuracy.
Next, we evaluate their performance on knowledge editing tasks to assess the potential impact on context-faithfulness.
The experimental results reveal that while these methods may yield inconsistent improvements in factual accuracy, they also cause a more severe decline in context-faithfulness, with the largest decrease reaching a striking 69.7\%.
To explain these declines, we analyze the hidden states and logit distributions for the tokens representing new knowledge and parametric knowledge respectively, highlighting the limitations of current approaches.
Our finding highlights the complex trade-offs inherent in enhancing LLMs.
Therefore, we recommend that more research on LLMs' factuality enhancement make efforts to reduce the sacrifice of context-faithfulness.

Primary Area: interpretability and explainable AI

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5973