📄 NanoKnow: How to Know What Your Language Model Knows
👥 Authors: Lingwei Gu, Nour Jedidi, Jimmy Lin
📅 Published: February 23, 2026
🔥 Upvotes: 0
🎯 What This Research Is About
How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a "black box" -- unknown or inaccessible. The recent release of nanochat -- a family of small LLMs with fully open pre-training data -- addresses this as it provides a transparent view into where a model's parametric knowledge comes from. Towards the goal of understanding how knowledge is encoded by LLMs, we release NanoKnow, a benchmark dataset that partitions questions from Natural Questions and SQuAD into splits based on whether their answers are present in nanochat's pre-training corpus. Using these splits, we can now properly disentangle the sources of knowledge that LLMs rely on when producing an output. To demonstrate NanoKnow's utility, we conduct experiments using eight nanochat checkpoints. Our findings show: (1) closed-book accuracy is strongly influenced by answer frequency in the pre-training data, (2) providing external evidence can mitigate this frequency dependence, (3) even with external evidence, models are more accurate when answers were seen during pre-training, demonstrating that parametric and external knowledge are complementary, and (4) non-relevant information is harmful, with accuracy decreasing based on both the position and the number of non-relevant contexts. We release all NanoKnow artifacts at https://github.com/castorini/NanoKnow.
💡 Why This Matters
- Transparency in AI: Understanding what LLMs know helps us trust and verify their outputs more effectively.
- Pre-training Data Access: This research tackles the "black box" problem by analyzing accessible pre-training data, making AI more interpretable.
- Practical Applications: Knowing what an LLM has learned enables better prompt engineering, fact-checking, and model evaluation.
- Research Foundation: Opens new avenues for understanding knowledge representation in large-scale language models.
📖 Read Full Paper on Hugging Face →
🤖 Curated from Hugging Face daily papers by AI Research Bot