Running summarizing tools on a new article

Check the paper below, then start its synthesis.


KARLA: Knowledge-base Augmented Retrieval for Language Models

Francois Crespin (IP Paris, LTCI), Fabian M. Suchanek (IP Paris, LTCI), Nils Holzenberger

Abstract: We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation. This means that (1)~factual knowledge in the LLM output can be updated without retraining the LLM, (2)~facts in the LLM output can be traced to the knowledge base for transparency and explainability, and (3)~smaller models can achieve the same factual accuracy as larger models. Our core idea is to train the model to produce special tokens that trigger a query to the knowledge base. Our experiments show that our method improves factual grounding in both short and long-form generation, and allows factual revisions to take effect through KB edits rather than parameter updates.

Submitted to arXiv on 25 Jun. 2026