Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.02708 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910902771515392 |
|---|---|
| author | Verma, Nikhil Bharadwaj, Manasa |
| author_facet | Verma, Nikhil Bharadwaj, Manasa |
| contents | Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages. Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalize to multilingual settings. To address this, we conduct a systematic analysis of distributional shifts in the embedding space of LLMs before and after alignment, uncovering its impact on model behavior across diverse languages. We leverage the alignment-induced separation in safety space as a quantitative tool to measure how alignment enforces safety constraints. Our study evaluates seven LLMs using balanced toxicity datasets and parallel text-detoxification benchmarks, revealing substantial disparities in the latent representation space between high-resource and low-resource languages. These findings underscore the need for language-specific fine-tuning to ensure fair, reliable and robust multilingual alignment. Our insights provide a foundation for developing truly safe multilingual LLMs, emphasizing the urgency of addressing alignment gaps in underrepresented languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02708 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context Verma, Nikhil Bharadwaj, Manasa Computation and Language Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages. Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalize to multilingual settings. To address this, we conduct a systematic analysis of distributional shifts in the embedding space of LLMs before and after alignment, uncovering its impact on model behavior across diverse languages. We leverage the alignment-induced separation in safety space as a quantitative tool to measure how alignment enforces safety constraints. Our study evaluates seven LLMs using balanced toxicity datasets and parallel text-detoxification benchmarks, revealing substantial disparities in the latent representation space between high-resource and low-resource languages. These findings underscore the need for language-specific fine-tuning to ensure fair, reliable and robust multilingual alignment. Our insights provide a foundation for developing truly safe multilingual LLMs, emphasizing the urgency of addressing alignment gaps in underrepresented languages. |
| title | The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.02708 |