SI-FACT: Mitigating Knowledge Conflict via Self-Improving Faithfulness-Aware Contrastive Tuning
This addresses the issue of unfaithful responses in knowledge-intensive tasks for users of LLMs, offering an incremental improvement with practical data efficiency.
The paper tackles the problem of knowledge conflict in large language models, where models prefer internal knowledge over provided context, by proposing a self-improving framework that automatically generates contrastive learning data and improves contextual recall rate by 6.2% over baselines.
Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we propose a novel self improving framework,Self Improving Faithfulness Aware Contrastive Tuning.The framework uses a self instruct mechanism that allows the base LLM to automatically generate high quality,structured contrastive learning data,including anchor samples,semantically equivalent positive samples,and negative samples simulating unfaithful scenarios.This approach significantly reduces the cost of manual annotation.Subsequently,contrastive learning is applied to train the model,enabling it to pull faithful responses closer and push unfaithful responses farther apart in the representation space.Experiments on knowledge conflict evaluation benchmarks ECARE KRE and COSE KRE show that the SI FACT model based on Llama3 8B Instruct improves the Contextual Recall Rate by 6.2% over the best baseline method,while significantly reducing dependence on internal memory.The results indicate that SI FACT provides strong effectiveness and high data efficiency in enhancing the contextual faithfulness of LLMs,offering a practical pathway toward building more proactive and trustworthy language models.