{
  "id": "2402.16837",
  "title": "Do Large Language Models Latently Perform Multi-Hop Reasoning?",
  "authors": "Sohee Yang, Elena Gribovskaya, Nora Kassner, Mor Geva, Sebastian Riedel",
  "first_public": "2024-02-26",
  "venue": "ACL 2024",
  "arxiv": "2402.16837",
  "paper_url": "https://arxiv.org/abs/2402.16837",
  "lens": [
    "analysis"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "depth-wise"
  ],
  "training": [
    "analysis-only"
  ],
  "questions": [
    "interpretability",
    "evaluation"
  ],
  "evidence": [
    "empirical",
    "probing"
  ],
  "modality": [
    "language"
  ],
  "summary": "Probes whether language models internally compose facts across hops before producing an answer, separating internal computation from verbal explanation.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Sohee Yang",
    "Elena Gribovskaya",
    "Nora Kassner",
    "Mor Geva",
    "Sebastian Riedel"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2402-16837",
  "citation_date": "2024-02-26",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/citation.csl.json",
  "publication": {
    "title": "Do Large Language Models Latently Perform Multi-Hop Reasoning?",
    "author_names": [
      "Sohee Yang",
      "Elena Gribovskaya",
      "Nora Kassner",
      "Mor Geva",
      "Sebastian Riedel"
    ],
    "year": 2024,
    "type": "paper-conference",
    "container_title": "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    "publisher": "Association for Computational Linguistics",
    "doi": "10.18653/v1/2024.acl-long.550",
    "pages": "10210-10229",
    "url": "https://aclanthology.org/2024.acl-long.550/",
    "source_url": "https://aclanthology.org/2024.acl-long.550/",
    "verified_at": "2026-10-18"
  },
  "publication_bibtex_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/publication.bib",
  "publication_csl_url": "https://latent-implicit-thinking.github.io/papers/2402.16837/publication.csl.json",
  "method_comparisons": [
    {
      "title": "Recovering information and testing its use",
      "text": "Recovering an intermediate answer from hidden states is different from showing that the model uses it. The multi-hop study by Yang and colleagues separates recall of a bridge entity from its contribution to the final answer, including interventions on internal representations. Evidence was stronger for the first hop than for the complete two-hop computation and varied by relation type. That distinction matters when interpreting claims that a model reasons internally.",
      "source_ids": [
        "2402.16837"
      ],
      "source_urls": [
        "https://aclanthology.org/2024.acl-long.550/"
      ],
      "source_labels": [
        "Yang et al. (2024)"
      ],
      "topic_id": "analysis",
      "topic_label": "Analysis and evaluation",
      "topic_url": "https://latent-implicit-thinking.github.io/topics/implicit-reasoning-evaluation/"
    }
  ]
}