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

arXiv: https://arxiv.org/abs/2509.08903 · HTML: https://mlsanity.com/paper/2509.08903/

## 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 (most cited first, 14 of 14)

- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Crawling the Internal Knowledge-Base of Language Models](https://mlsanity.com/paper/2301.12810/) (2023)
- [ALCUNA: Large Language Models Meet New Knowledge](https://mlsanity.com/paper/2310.14820/) (2023)
- [Retrieving Supporting Evidence for Generative Question Answering](https://mlsanity.com/paper/2309.11392/) (2023)
- [MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization](https://mlsanity.com/paper/2407.04118/) (2024)
- [Evaluating Language Models for Knowledge Base Completion](https://mlsanity.com/paper/2303.11082/) (2023)
- [Enabling LLM Knowledge Analysis via Extensive Materialization](https://mlsanity.com/paper/2411.04920/) (2024)
- [Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons](https://mlsanity.com/paper/2502.02988/) (2025)
- [An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models](https://mlsanity.com/paper/2109.02772/) (2021)
- [Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction](https://mlsanity.com/paper/2404.12957/) (2024)

## 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.