arXiv:2606. 26807v1 Announce Type: new Abstract: We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 07707v1 Announce Type: cross Abstract: Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights.
arXiv:2604. 07590v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources.
The paper introduces KBevo, a co‑evolving framework that simultaneously builds a structured knowledge base and performs reasoning over it for knowledge‑intensive question answering. By optimizing both components end‑to‑end with QA outcome rewards, the system improves the quality and connectivity of the knowledge base, leading to higher answer reachability and better compositional factual reasoning. Compared to standard retrieval baselines, KBevo offers greater controllability and improved factual accuracy.
ConvergeWriter introduces a bottom‑up, data‑driven framework for long‑form document generation that first retrieves exhaustive knowledge from a source corpus and clusters it into distinct knowledge groups. These clusters then guide the creation of a hierarchical outline and the final text, ensuring the output is strictly grounded in the retrieved material and traceable to its sources. Experiments on 14B and 32B LLMs show that this approach matches or surpasses state‑of‑the‑art baselines, especially in scenarios requiring high factual fidelity and structural coherence.
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon of...
The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.