{"ID":2872742,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.08903","arxiv_id":"2509.08903","title":"Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC","abstract":"RAG and fine-tuning are prevalent strategies for improving the quality of LLM outputs. However, in constrained situations, such as that of the 2025 LM-KBC challenge, such techniques are restricted. In this work we investigate three facets of the triple completion task: generation, quality assurance, and LLM response parsing. Our work finds that in this constrained setting: additional information improves generation quality, LLMs can be effective at filtering poor quality triples, and the tradeoff between flexibility and consistency with LLM response parsing is setting dependent.","short_abstract":"RAG and fine-tuning are prevalent strategies for improving the quality of LLM outputs. However, in constrained situations, such as that of the 2025 LM-KBC challenge, such techniques are restricted. In this work we investigate three facets of the triple completion task: generation, quality assurance, and LLM response pa...","url_abs":"https://arxiv.org/abs/2509.08903","url_pdf":"https://arxiv.org/pdf/2509.08903v1","authors":"[\"Alex Clay\",\"Ernesto Jiménez-Ruiz\",\"Pranava Madhyastha\"]","published":"2025-09-10T18:04:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}