CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
Large Language Models (LLMs) are pretrained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. Ideally, while LLMs should provide consistent responses to culture-independent questions across languages, we observe significant performance disparities. To address this, we explore the Cross-Lingual Self-Aligning ability of Language Models (CALM) to align knowledge across languages. Specifically, for a given question, we sample multiple responses across different languages, and select the most self-consistent response as the target, leaving the remaining responses as negative examples. We then employ direct preference optimization (DPO) to align the model's knowledge across different languages. Evaluations on the MEDQA and X-CSQA datasets demonstrate CALM's effectiveness in enhancing cross-lingual knowledge question answering, both in zero-shot and retrieval augmented settings. We also found that increasing the number of languages involved in CALM training leads to even higher accuracy and consistency. We offer a qualitative analysis of how cross-lingual consistency can enhance knowledge alignment and explore the method's generalizability. The source code and data of this paper are available on GitHub.
Code (0)
등록된 구현이 없습니다.
Tasks
General KnowledgeLanguage ModelingLanguage ModellingMedQAQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calcium traces, existing approaches remain task-specific, limiting transfer across…
CALM: Culturally Self-Aware Language Models
Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evol…
Contrastive LearningCalibrated Multimodal Representation Learning with Missing Modalities
Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but req…
Representation LearningCALM: Consensus-Aware Localized Merging for Multi-Task Learning
Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified int…
Multi-Task LearningTask ArithmeticCross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highes…