Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.
Code-mixed llm: Improve large language models’ capability to handle code-mixing through reinforcement learning from ai feedback.arXiv preprint arXiv:2411.09073,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.