4 papers
Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment
Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1
Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For ins…
To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios
Sotaro Takeshita, Yurina Takeshita, Simone Paolo Ponzetto +1
Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply t…
Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks
Sotaro Takeshita, Yurina Takeshita, Daniel Ruffinelli +1
In this paper, we study the surprising impact that truncating text embeddings has on downstream performance. We consistently observe across 6 state-of-the-art text encoders and 26…
Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
Alina Klerings, Jannik Brinkmann, Daniel Ruffinelli +1
Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely…