paper-with-me

Papers

Cross-Lingual Exploration for Parametric Knowledge

2026-06-23 · Elisha Diskind, Itamar Trainin, Uri Shaham, Leshem Choshen, Idan Szpektor, Omri Abend arxiv

Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, leading to failures in cross-lingual knowledge transfer and consistency. In this work, we investigate techniques for accessing hidden factual knowledge by exploring cross-lingual prompting strategies. We identify four inherent dimensions of cross-lingual exploration that directly govern parametric knowledge retrieval and evaluate them on multilingual factual benchmarks covering 17 typologically diverse languages. Our results demonstrate that cross-lingual exploration significantly improves knowledge transfer and factual recall, representing a more efficient compute Pareto frontier than native-language scaling. Furthermore, we observe corresponding improvements in cross-lingual consistency, exceeding what can be explained by accuracy gains alone. Overall, our work establishes multilingual prompt exploration as a highly effective inference-time strategy for unlocking latent parametric knowledge.

📄 PDF Abstract BibTeX arXiv:2606.24579

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Knowledge-Grounded Natural Language Understanding and Generation

2024-03-22 · Chenxi Whitehouse

This thesis investigates how natural language understanding and generation with transformer models can benefit from grounding the models with knowledge representations and addresses the following key research questions: …

Cross-Lingual TransferEntity LinkingFake News DetectionNatural Language Understanding+1

Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts

2026-03-17 · Lucas Bandarkar, Alan Ansell, Trevor Cohn arxiv

In this work, we analyze shortcomings in cross-lingual knowledge transfer in large, modern reasoning LLMs. We demonstrate that the perceived gap in knowledge transfer is primarily a script barrier. First, we conduct an o…

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning

2024-06-25 · Ercong Nie, Bo Shao, Zifeng Ding, Mingyang Wang 외

Large language models (LLMs) possess extensive parametric knowledge, but this knowledge is difficult to update with new information because retraining is very expensive and infeasible for closed-source models. Knowledge …

In-Context Learningknowledge editingTransfer Learning

Effects of Cross-lingual Evidence in Multilingual Medical Question Answering

2026-04-22 · Anar Yeginbergen, Maite Oronoz, Rodrigo Agerri arxiv

This paper investigates Multilingual Medical Question Answering across high-resource (English, Spanish, French, Italian) and low-resource (Basque, Kazakh) languages. We evaluate three types of external evidence sources a…

Question Answering

Evaluating the External and Parametric Knowledge Fusion of Large Language Models

2024-05-29 · Hao Zhang, Yuyang Zhang, Xiaoguang Li, Wenxuan Shi 외

Integrating external knowledge into large language models (LLMs) presents a promising solution to overcome the limitations imposed by their antiquated and static parametric memory. Prior studies, however, have tended to …