{
  "schema": "https://miscsubjects.com/schemas/jarticle.json",
  "status": "published",
  "slug": "fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
  "title": "Sharma et al. (2023) — sycophancy in language models",
  "type": "article",
  "kind": "precedent",
  "body": [
    "Citation: Sharma M, Tong M, Korbak T, Duvenaud D, Askell A, Bowman SR, Cheng N, Durmus E, Hatfield-Dodds Z, Johnston SR, Kravec S, Maxwell T, McCandlish S, Ndousse K, Rausch O, Schiefer N, Yan D, Zhang M, Perez E. \"Towards Understanding Sycophancy in Language Models.\" arXiv:2310.13548 (submitted 20 Oct 2023; version 4 revised 10 May 2025). License: CC BY 4.0 (arXiv listing).",
    "Identifiers: arXiv:2310.13548.",
    "Retrieved from: https://export.arxiv.org/api/query?id_list=2310.13548 (listing also at https://arxiv.org/abs/2310.13548)",
    "Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in models whose finetuning procedure made use of human feedback, and the potential role of human preference judgments in such behavior. We first demonstrate that five state-of-the-art AI assistants consistently exhibit sycophancy across four varied free-form text-generation tasks. To understand if human preferences drive this broadly observed behavior, we analyze existing human preference data. We find that when a response matches a user's views, it is more likely to be preferred. Moreover, both humans and preference models (PMs) prefer convincingly-written sycophantic responses over correct ones a non-negligible fraction of the time. Optimizing model outputs against PMs also sometimes sacrifices truthfulness in favor of sycophancy. Overall, our results indicate that sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses."
  ],
  "facts": {
    "kind": "precedent",
    "citation": "Sharma M, Tong M, Korbak T, Duvenaud D, Askell A, Bowman SR, Cheng N, Durmus E, Hatfield-Dodds Z, Johnston SR, Kravec S, Maxwell T, McCandlish S, Ndousse K, Rausch O, Schiefer N, Yan D, Zhang M, Perez E. \"Towards Understanding Sycophancy in Language Models.\" arXiv:2310.13548 (submitted 20 Oct 2023; version 4 revised 10 May 2025). License: CC BY 4.0 (arXiv listing).",
    "identifiers": "arXiv:2310.13548.",
    "retrieval_url": "https://export.arxiv.org/api/query?id_list=2310.13548",
    "passage_status": "verbatim abstract"
  },
  "ontology": {
    "above": [
      "fn-index-precedents"
    ],
    "below": [],
    "adjacent": [],
    "nested": []
  },
  "created": "2026-10-11T07:07:19.929Z",
  "updated": "2026-10-11T07:07:19.929Z",
  "version": 1,
  "hash": "05a207a25fba6ca05bc463ea6ff8872d4f6d751921c3fd399d49a44c5804ff3a",
  "styling": {
    "scope": "shared",
    "how": "no value on the page is set by hand: each comes from this theme, and each theme value becomes the CSS variable named beside it. PATCH https://miscsubjects.com/api/jarticles/theme changes them.",
    "widget_style": {
      "what": "every widget may carry style: {…}; these are the only keys it reads",
      "rotate": "degrees, a number",
      "offset_x": "pixels, a number",
      "offset_y": "pixels, a number",
      "pulse": "true to pulse"
    },
    "theme": {
      "color": {
        "page_bg": "#f5f5f7",
        "sheet_bg": "#ffffff",
        "ink": "#1d1d1f",
        "soft": "#424245",
        "muted": "#6e6e73",
        "dim": "#86868b",
        "line": "#d2d2d7",
        "accent": "#0071e3",
        "accent_soft": "rgba(0,113,227,0.08)",
        "link": "#0066cc",
        "selection": "rgba(0,113,227,0.18)",
        "widget_bg": "#f5f5f7",
        "widget_border": "#d2d2d7",
        "card_bg": "#ffffff",
        "code_bg": "#f5f5f7",
        "json_bg": "#161b19",
        "json_ink": "#e6e1d4",
        "json_key": "#7fd3c3",
        "json_string": "#e9c46a",
        "json_number": "#f4a261",
        "json_bool": "#c792ea",
        "json_null": "#928d7e",
        "json_punct": "#6b6759",
        "json_bar": "#0e1512",
        "kind_badge_bg": "#0e6e60",
        "kind_badge_ink": "#ffffff"
      },
      "color_dark": {
        "page_bg": "#000000",
        "sheet_bg": "#1d1d1f",
        "ink": "#f5f5f7",
        "soft": "#d2d2d7",
        "muted": "#a1a1a6",
        "dim": "#86868b",
        "line": "#424245",
        "accent": "#2997ff",
        "accent_soft": "rgba(41,151,255,0.12)",
        "link": "#2997ff",
        "selection": "rgba(41,151,255,0.25)",
        "widget_bg": "#2c2c2e",
        "widget_border": "#424245",
        "card_bg": "#1d1d1f",
        "code_bg": "#2c2c2e",
        "json_bg": "#0a0d0c",
        "json_ink": "#e6e1d4",
        "json_key": "#7fd3c3",
        "json_string": "#e9c46a",
        "json_number": "#f4a261",
        "json_bool": "#c792ea",
        "json_null": "#757062",
        "json_punct": "#5d665f",
        "json_bar": "#060807",
        "kind_badge_bg": "#4fc1ab",
        "kind_badge_ink": "#0b0f0d"
      },
      "font": {
        "display": "-apple-system,BlinkMacSystemFont,\"SF Pro Display\",\"SF Pro Text\",\"Helvetica Neue\",Helvetica,Arial,sans-serif",
        "body": "-apple-system,BlinkMacSystemFont,\"SF Pro Display\",\"SF Pro Text\",\"Helvetica Neue\",Helvetica,Arial,sans-serif",
        "mono": "ui-monospace,SFMono-Regular,\"SF Mono\",Menlo,Consolas,monospace",
        "google_fonts": ""
      },
      "size": {
        "body": "17px",
        "small": "17px",
        "eye": "17px",
        "lead": "17px",
        "h1": "52px",
        "h2": "34px",
        "h3": "22px",
        "byline": "17px",
        "h1_measure": "none",
        "code": "17px",
        "json": "17px",
        "widget_title": "17px"
      },
      "leading": {
        "body": "1.7",
        "head": "1.18",
        "lead": "1.5",
        "json": "1.6"
      },
      "weight": {
        "display": "700",
        "head": "700",
        "body": "400",
        "strong": "700",
        "eye": "700"
      },
      "tracking": {
        "eye": "0.14em",
        "display": "-0.03em",
        "body": "-0.006em",
        "badge": "0.08em"
      },
      "layout": {
        "sheet_width": "1000px",
        "text_width": "880px",
        "gutter": "16px",
        "sheet_padding": "56px 64px 64px",
        "sheet_padding_mobile": "24px 18px 40px",
        "sheet_margin": "28px auto 72px",
        "block_gap": "1.15em",
        "widget_gap": "28px",
        "grid_gap": "14px"
      },
      "border": {
        "sheet": "0px solid",
        "sheet_radius": "30px",
        "widget": "1px solid",
        "widget_radius": "24px",
        "card_radius": "24px",
        "badge_radius": "999px",
        "rule": "1px solid",
        "code_radius": "18px",
        "accent_bar": "3px"
      },
      "shadow": {
        "sheet": "0 1px 1px rgba(0,0,0,.02),0 6px 26px rgba(0,0,0,.05)",
        "widget": "none",
        "card_hover": "0 10px 28px -16px rgba(28,27,23,0.35)"
      },
      "motion": {
        "hover": "160ms ease"
      }
    }
  },
  "page": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
  "json": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models.json",
  "markdown": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models.md",
  "theme": "https://miscsubjects.com/article-theme.json",
  "calls": [
    {
      "what": "this article as a page (no key)",
      "method": "GET",
      "url": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
      "headers": {}
    },
    {
      "what": "this article as its object (no key)",
      "method": "GET",
      "url": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models.json",
      "headers": {}
    },
    {
      "what": "this article as Markdown (no key)",
      "method": "GET",
      "url": "https://miscsubjects.com/a/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models.md",
      "headers": {}
    },
    {
      "what": "the object with its hash, drafts too",
      "method": "GET",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)"
      }
    },
    {
      "what": "one piece and that piece’s hash",
      "method": "GET",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models/at?path=facts",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)"
      }
    },
    {
      "what": "grep: every key or value that matches, with the path to change it",
      "method": "GET",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models/grep?q=owner",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)"
      }
    },
    {
      "what": "change pieces (set, merge, delete, append, insert, move); if-match is the hash",
      "method": "PATCH",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)",
        "content-type": "application/json",
        "if-match": "<hash from the read>"
      },
      "body": {
        "ops": [
          {
            "op": "set",
            "path": "facts.example",
            "value": 1
          }
        ]
      }
    },
    {
      "what": "replace the whole object",
      "method": "PUT",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)",
        "content-type": "application/json",
        "if-match": "<hash>"
      },
      "body": {
        "slug": "fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models",
        "title": "…"
      }
    },
    {
      "what": "fetch every source, hash what came back and check the quote is in it",
      "method": "POST",
      "url": "https://miscsubjects.com/api/jarticles/fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models/verify",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)",
        "content-type": "application/json"
      },
      "body": {}
    },
    {
      "what": "an Obsidian-style command",
      "method": "POST",
      "url": "https://miscsubjects.com/api/jarticles/cli",
      "headers": {
        "x-sheets-key": "$(cat /Users/cyrusmassoumi/.misc-sheets-key)",
        "content-type": "application/json"
      },
      "body": {
        "command": "backlinks",
        "file": "fn-prec-08-sharma-et-al-2023-sycophancy-in-language-models"
      }
    }
  ]
}