AnchorPrompt: פומפט עצמאי: פומפטים רכים למודלי שפה-אודיו רב-גדול

תקציר מקורי באנגליתarXiv:2610.00706v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and question embeddings. We train these vectors through self-distillation over diverse audio and text perturbations. To improve answer consistency and mitigate hallucination, we use the model's prediction on the clean recording as the target for answerable inputs, and assign a refusal target when the audio lacks sufficient evidence to answer. Furthermore, AnchorPrompt is perturbation-agnostic at inference, requiring no prior detect