Showing 2025Show all
2 papers · 1 filter
cs.LG2025
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…
cs.CL2025
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…