{
  "id": "2310.05707",
  "title": "Guiding Language Model Reasoning with Planning Tokens",
  "authors": "Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan, William Yang Wang, Alessandro Sordoni",
  "first_public": "2023-10-09",
  "venue": "COLM 2024",
  "arxiv": "2310.05707",
  "paper_url": "https://arxiv.org/abs/2310.05707",
  "code_url": "https://github.com/WANGXinyiLinda/planning_tokens",
  "lens": [
    "learned-tokens"
  ],
  "representation": [
    "discrete-token"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "capability",
    "controllability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "language"
  ],
  "summary": "Adds a learned planning token before each written reasoning step, then uses that token to guide the step.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Xinyi Wang",
    "Lucas Caccia",
    "Oleksiy Ostapenko",
    "Xingdi Yuan",
    "William Yang Wang",
    "Alessandro Sordoni"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2310.05707/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2310-05707",
  "citation_date": "2023-10-09",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2310.05707/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2310.05707/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2310.05707/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2310.05707/citation.csl.json",
  "method_comparisons": [
    {
      "title": "Pausing and planning",
      "text": "Pause tokens add computation before the answer without choosing a different plan token for each step. Planning tokens instead select a learned token before generating each written reasoning step. The latter still produces a textual chain of thought. In the pause-token experiments, the training setup matters: gains were strongest when pauses were used in both pretraining and fine-tuning, not simply inserted into an unchanged model.",
      "source_ids": [
        "2310.02226",
        "2310.05707"
      ],
      "source_urls": [
        "https://proceedings.iclr.cc/paper_files/paper/2024/hash/76917808731dae9e6d62c2a7a6afb542-Abstract-Conference.html",
        "https://arxiv.org/html/2310.05707v3#S2"
      ],
      "source_labels": [
        "Pause-token paper",
        "Planning-token paper, §2"
      ],
      "topic_id": "learned-tokens",
      "topic_label": "Thinking tokens",
      "topic_url": "https://latent-implicit-thinking.github.io/topics/thinking-tokens/"
    }
  ]
}