{
  "id": 16554909,
  "title": "Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery",
  "url": "https://urgent.news/2026/10/23/interpretable-sparse-fine-tuning-with-topklora-enables-faithful",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-23T16:37:29.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.32866v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Fine-tuning on datasets of unknown origin can create a backdoor in the trained model when the data includes poisoned examples. Difficult to localise and remove, backdoors can persist through safety training. While parameter-efficient fine-tuning methods capture the full parameter changes introduced during training, they are not easily interpretable. We present the full method of TopKLoRA,…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}