Does Context Compression Preserve Refusal Alignment?
Context compression reduces inference cost by encoding inputs into compact representations while preserving semantic content. An open question is whether semantic preservation alone is sufficient to maintain downstream behaviours such as refusal alignment. We investigate this question and find that encoder-based compression systematically weakens refusal behaviour in instruction-tuned language…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
