While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern. One key feature is the ability to refuse or deflect harmful, malicious, or insensitive prompts. In this paper, we expose safety vulnerabilities across six common op …
Text embedding models trained with contrastive learning learn to follow task instructions from instruction-paired data, while instruction-tuned LLMs already know how to follow them. We show that this instruction-following ability can carry over from an LLM to a Transformer-based embedder without any training. We propos …
Contrastive learning is a successful paradigm for learning $d$-dimensional geometric representations from a collection of ``anchor--positive--negative'' triplets $(i,j^{+},k^{-})$, indicating that ``item $i$ is closer to $j$ than to $k$.'' Despite its success, understanding why contrastive learning leads to representat …