{
  "id": "2405.08644",
  "title": "Thinking Tokens for Language Modeling",
  "authors": "David Herel, Tomas Mikolov",
  "first_public": "2023-09-04",
  "first_public_source": "https://aitp-conference.org/2023/",
  "first_public_note": "AITP presentation date; the earlier public release date of the conference abstract is unverified.",
  "citation_date": "2024-05-14",
  "venue": "AITP 2023",
  "arxiv": "2405.08644",
  "paper_url": "https://arxiv.org/abs/2405.08644",
  "lens": [
    "learned-tokens"
  ],
  "representation": [
    "discrete-token"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Gives a recurrent language model extra hidden-state updates by inserting special tokens after each word. Tests whether these updates improve next-word prediction.",
  "provenance": "Primary-source literature search, 2026-09-04",
  "author_names": [
    "David Herel",
    "Tomas Mikolov"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2405.08644/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2405-08644",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2405.08644/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2405.08644/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2405.08644/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2405.08644/citation.csl.json"
}