AI RESEARCH
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
arXiv CS.LG
•
ArXi:2505.24859v3 Announce Type: replace Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. While predominantly studied for multiple-choice and toy tasks, their effectiveness in free-form generation remains largely unexplored. Moving "Beyond Multiple Choice," we evaluate steering vectors for controlling topical focus, sentiment, toxicity, and readability in abstractive summaries across the SAMSum, NEWTS, and arXi datasets.