# Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

arXiv: https://arxiv.org/abs/2504.13816 · HTML: https://mlsanity.com/paper/2504.13816/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding](https://mlsanity.com/paper/2009.05387/) (2020)
- [The Geometry of Multilingual Language Model Representations](https://mlsanity.com/paper/2205.10964/) (2022)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation](https://mlsanity.com/paper/2402.11493/) (2024)
- [SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages](https://mlsanity.com/paper/2407.19672/) (2024)
- [Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?](https://mlsanity.com/paper/2311.03788/) (2023)
- [Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners](https://mlsanity.com/paper/2405.13816/) (2024)
- [Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization](https://mlsanity.com/paper/2305.01951/) (2023)
- [Revealing the Parallel Multilingual Learning within Large Language Models](https://mlsanity.com/paper/2403.09073/) (2024)

## Built on by (most cited first, 6 of 6)

- [Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness](https://mlsanity.com/paper/2510.09033/) (2025)
- [Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency](https://mlsanity.com/paper/2603.17102/) (2026)
- [Understanding the Behaviors of Environment-aware Information Retrieval](https://mlsanity.com/paper/2606.16817/) (2026)
- [Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction](https://mlsanity.com/paper/2602.00959/) (2026)
- [Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training](https://mlsanity.com/paper/2605.11416/) (2026)
- [The Geometry of Knowledge Accessibility in Large Language Models](https://mlsanity.com/paper/2610.03052/) (2026)

## Abstract (arXiv)

While understanding the knowledge boundaries of LLMs is crucial to prevent hallucination, research on the knowledge boundaries of LLMs has predominantly focused on English. In this work, we present the first study to analyze how LLMs recognize knowledge boundaries across different languages by probing their internal representations when processing known and unknown questions in multiple languages. Our empirical studies reveal three key findings: 1) LLMs' perceptions of knowledge boundaries are encoded in the middle to middle-upper layers across different languages. 2) Language differences in knowledge boundary perception follow a linear structure, which motivates our proposal of a training-free alignment method that effectively transfers knowledge boundary perception ability across languages, thereby helping reduce hallucination risk in low-resource languages; 3) Fine-tuning on bilingual question pair translation further enhances LLMs' recognition of knowledge boundaries across languages. Given the absence of standard testbeds for cross-lingual knowledge boundary analysis, we construct a multilingual evaluation suite comprising three representative types of knowledge boundary data. Our code and datasets are publicly available at https://github.com/DAMO-NLP-SG/LLM-Multilingual-Knowledge-Boundaries.