# Certifying Knowledge Comprehension in LLMs

arXiv: https://arxiv.org/abs/2402.15929 · HTML: https://mlsanity.com/paper/2402.15929/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 61 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://mlsanity.com/paper/2402.07630/) (2024)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [How well do Large Language Models perform in Arithmetic tasks?](https://mlsanity.com/paper/2304.02015/) (2023)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [An LLM can Fool Itself: A Prompt-Based Adversarial Attack](https://mlsanity.com/paper/2310.13345/) (2023)
- [Are Emergent Abilities in Large Language Models just In-Context Learning?](https://mlsanity.com/paper/2309.01809/) (2023)
- [On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)](https://mlsanity.com/paper/2302.06706/) (2023)
- [Robustness Verification for Transformers](https://mlsanity.com/paper/2002.06622/) (2020)
- [Bypassing the Safety Training of Open-Source LLMs with Priming Attacks](https://mlsanity.com/paper/2312.12321/) (2023)
- [Understanding the Capabilities of Large Language Models for Automated Planning](https://mlsanity.com/paper/2305.16151/) (2023)
- [Scalable Quantitative Verification For Deep Neural Networks](https://mlsanity.com/paper/2002.06864/) (2020)
- [Inductive Relation Prediction by BERT](https://mlsanity.com/paper/2103.07102/) (2021)
- [Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning](https://mlsanity.com/paper/2310.13552/) (2023)
- [Robustness Certification of Generative Models](https://mlsanity.com/paper/2004.14756/) (2020)
- [Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisis](https://mlsanity.com/paper/2201.08174/) (2022)

## Built on by (most cited first, 1 of 1)

- [Quantitative Certification of Agentic Tool Selection](https://mlsanity.com/paper/2510.03992/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed in safety-critical systems where they provide answers based on in-context information derived from knowledge bases. As LLMs are increasingly envisioned as superhuman agents, their proficiency in knowledge comprehension-extracting relevant information and reasoning over it to answer questions, a key facet of human intelligence-becomes crucial. However, existing evaluations of LLMs on knowledge comprehension are typically conducted on small test sets, but these datasets represent only a tiny fraction of the vast number of possible queries. Simple empirical evaluations on these limited test sets raises concerns about the reliability and generalizability of the results. In this work, we introduce the first specification and certification framework for knowledge comprehension in LLMs, providing formal probabilistic guarantees for reliability. Instead of a fixed dataset, we design novel specifications that mathematically represent prohibitively large probability distributions of knowledge comprehension prompts with natural noise, using knowledge graphs. From these specifications, we generate quantitative certificates that offer high-confidence, tight bounds on the probability that a given LLM correctly answers any question drawn from the specification distribution. We apply our framework to certify SOTA LLMs in two domains: precision medicine and general question-answering. Our results reveal previously unrecognized vulnerabilities in SOTA LLMs due to natural noise in the prompts. Additionally, we establish performance hierarchies with formal guarantees among the SOTA LLMs, particularly in the context of precision medicine question-answering.