Search papers, labs, and topics across Lattice.
This paper introduces VAKE, a two-stage reinforcement-learning framework designed to enhance the recall and verification of factual knowledge in Large Language Models (LLMs) by separating the processes of knowledge elicitation and reasoning. By employing explicit priming to insert verifiable evidence into the input context, VAKE enables models to access latent parametric knowledge, which is then utilized in an implicit reasoning stage to generate answers. Experimental results demonstrate that VAKE significantly outperforms standard baselines across multiple benchmarks, revealing that over 80% of the inserted triples provide essential knowledge not derivable from the original context.
VAKE reveals that over 80% of the knowledge activated through explicit priming is crucial for answering questions, showcasing a new pathway to enhance LLM factual accuracy.
Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods entangle knowledge elicitation with reasoning, making it difficult to determine whether correct answers arise from parametric knowledge or the input context. To address this challenge, we propose VAKE (Verifiable Activation of Parametric KnowledgE), a two-stage reinforcement-learning framework that externalizes latent parametric knowledge through explicit Priming and transfers the acquired elicitation capability to implicit Reasoning. Given a query and an insufficient retrieved subgraph, the Priming policy explicitly inserts bridging triples as verifiable evidence, with supervision provided by rewards derived from answers generated by a separate frozen model over the augmented subgraph. Building on the policy learned during Priming, the Reasoning stage trains the model to answer from the original input, testing whether the capability acquired through explicit knowledge elicitation transfers to implicit reasoning. Experiments across seven benchmarks and models from 3B to 14B show that VAKE consistently outperforms standard baselines, including when transferring directly from HotpotQA to OOD datasets. LLM-based evaluation further shows that over 80% of the inserted triples provide factual bridging knowledge not derivable from the retrieved context, while more than half elicit knowledge inaccessible through direct prompting. These results suggest that VAKE activates latent parametric knowledge rather than copying the input context or memorizing dataset-specific associations.
