{
  "annotation_id": "6e8e4e2e-004a-424c-b54e-e91a9b1b09d8",
  "date_created": "2026-02-17T05:53:12.485000Z",
  "date_modified": "2026-02-17T05:53:12.485000Z",
  "file_hash": "f4aabfad91ea1415dffea5d5bb2dbfeef18d054a35618e28677518e140610f0f",
  "private": false,
  "record": {
    "abstract": "It has been shown that Large Reasoning Models (LRMs) may not *say what they think*: they do not always volunteer information about how certain parts of the input influence their reasoning. But it is one thing for a model to *omit* such information and another, worse thing to *lie* about it. Here, we extend the work of Chen et al. (2025) to show that LRMs will do just this: they will flatly deny relying on hints provided in the prompt in answering multiple choice questions -- even when directly asked to reflect on unusual (i.e. hinted) prompt content, even when allowed to use hints, and even though experiments *show* them to be using the hints. Our results thus have discouraging implications for CoT monitoring and interpretability.",
    "arxiv_id": "2601.07663",
    "authors": [
      "William Walden"
    ],
    "categories": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "title": "Reasoning Models Will Blatantly Lie About Their Reasoning",
    "url": "https://arxiv.org/abs/2601.07663",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "1ef32dc3-79b6-4fa9-b96c-126b5fadd272",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}