{
  "annotation_id": "d34dc5a9-3312-487e-ae57-96ebbdfd74aa",
  "date_created": "2026-02-17T05:53:12.489000Z",
  "date_modified": "2026-02-17T05:53:12.489000Z",
  "file_hash": "86d6d529e11612d635f77f5eb7c2d4fcf7f1a395d529204bc7a9e2a609d02c3d",
  "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": "v2"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "7c9ea5e4-acd7-4d56-ac69-cb682b82d905",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}