mlsanityData to 14 Oct 2026

Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC

arXiv 2509.08903 ↗First posted 10 Sep 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 10 Sep 2025.

Builds on

14 of 16 references.

References · 14

  1. 2019Language Models as Knowledge Bases?cited by 1,936
  2. 2019How Can We Know What Language Models Know?cited by 959
  3. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  4. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 265
  5. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  6. 2023Crawling the Internal Knowledge-Base of Language Modelscited by 85
  7. 2023ALCUNA: Large Language Models Meet New Knowledgecited by 35
  8. 2023Retrieving Supporting Evidence for Generative Question Answeringcited by 31
  9. 2024MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimizationcited by 21
  10. 2023Evaluating Language Models for Knowledge Base Completioncited by 20
  11. 2024Enabling LLM Knowledge Analysis via Extensive Materializationcited by 12
  12. 2025Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessonscited by 9
2 more
  1. 2021An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Modelscited by 8
  2. 2024Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extractioncited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
  2. 2026How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws
  3. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
  4. 2025Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems
  5. 2023Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
  6. 2024Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations
  7. 2026LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB
  8. 2026A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data