{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 🎯 White-Box Uncertainty Quantification\n", "\n", "
\n", "

\n", " White-box Uncertainty Quantification (UQ) methods leverage token probabilities to estimate uncertainty. Multi-generation white-box methods generate multiple responses from the same prompt, combining the sampling approach of black-box UQ with token-probability-based singals. This demo provides an illustration of how to use state-of-the-art white-box UQ methods with uqlm. The following multi-generation scorers are available:\n", "

\n", " \n", "* Monte carlo sequence probability ([Kuhn et al., 2023](https://arxiv.org/abs/2302.09664))\n", "* Consistency and Confidence (CoCoA) ([Vashurin et al., 2025](https://arxiv.org/abs/2502.04964))\n", "* Semantic Negentropy ([Farquhar et al., 2024](https://www.nature.com/articles/s41586-024-07421-0)) \n", "* Semantic Density ([Qiu et al., 2024](https://arxiv.org/abs/2405.13845))\n", "* P(True) ([Kadavath et al., 2022](https://arxiv.org/abs/2207.05221))\n", "\n", "
\n", "\n", "## 📊 What You'll Do in This Demo\n", "\n", "
\n", "
1
\n", "
\n", "

Set up LLM and prompts.

\n", "

Set up LLM instance and load example data prompts.

\n", "
\n", "
\n", "\n", "
\n", "
2
\n", "
\n", "

Generate LLM Responses and Confidence Scores

\n", "

Generate and score LLM responses to the example questions using the WhiteBoxUQ() class.

\n", "
\n", "
\n", "\n", "
\n", "
3
\n", "
\n", "

Evaluate Hallucination Detection Performance

\n", "

Visualize model accuracy at different thresholds of the various white-box UQ confidence scores. Compute precision, recall, and F1-score of hallucination detection.

\n", "
\n", "
\n", "\n", "## ⚖️ Advantages & Limitations\n", "\n", "
\n", "
\n", "

Pros

\n", " \n", "
\n", " \n", "
\n", "

Cons

\n", " \n", "
\n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "tags": [] }, "outputs": [], "source": [ "import numpy as np\n", "from sklearn.metrics import precision_score, recall_score, f1_score\n", "\n", "from uqlm import WhiteBoxUQ\n", "from uqlm.utils import load_example_dataset, math_postprocessor, plot_model_accuracies, Tuner" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 1. Set up LLM and Prompts" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In this demo, we will illustrate this approach using a set of math questions from the [gsm8k benchmark](https://github.com/openai/grade-school-math). To implement with your use case, simply **replace the example prompts with your data**. " ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Loading dataset - gsm8k...\n", "Processing dataset...\n", "Dataset ready!\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questionanswer
0Natalia sold clips to 48 of her friends in Apr...72
1Weng earns $12 an hour for babysitting. Yester...10
2Betty is saving money for a new wallet which c...5
3Julie is reading a 120-page book. Yesterday, s...42
4James writes a 3-page letter to 2 different fr...624
\n", "
" ], "text/plain": [ " question answer\n", "0 Natalia sold clips to 48 of her friends in Apr... 72\n", "1 Weng earns $12 an hour for babysitting. Yester... 10\n", "2 Betty is saving money for a new wallet which c... 5\n", "3 Julie is reading a 120-page book. Yesterday, s... 42\n", "4 James writes a 3-page letter to 2 different fr... 624" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Load example dataset (gsm8k)\n", "gsm8k = load_example_dataset(\"gsm8k\", n=100)\n", "gsm8k.head()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "tags": [] }, "outputs": [], "source": [ "# Define prompts\n", "MATH_INSTRUCTION = \"When you solve this math problem only return the answer with no additional text.\\n\"\n", "prompts = [MATH_INSTRUCTION + prompt for prompt in gsm8k.question]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In this example, we use `AzureChatOpenAI` to instantiate our LLM, but any [LangChain Chat Model](https://js.langchain.com/docs/integrations/chat/) may be used. Be sure to **replace with your LLM of choice.**" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "tags": [] }, "outputs": [], "source": [ "# import sys\n", "# !{sys.executable} -m pip install python-dotenv\n", "# !{sys.executable} -m pip install langchain-openai\n", "\n", "# # User to populate .env file with API credentials. In this step, replace with your LLM of choice.\n", "from dotenv import load_dotenv, find_dotenv\n", "from langchain_openai import AzureChatOpenAI\n", "\n", "load_dotenv(find_dotenv())\n", "llm = AzureChatOpenAI(deployment_name=\"gpt-4o\", openai_api_type=\"azure\", openai_api_version=\"2024-02-15-preview\", temperature=1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "## 2. Generate responses and confidence scores" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### `WhiteBoxUQ()` - Generate LLM responses and compute token-probability-based confidence scores for each response.\n", "\n", "![Sample Image](https://raw.githubusercontent.com/cvs-health/uqlm/develop/assets/images/white_box_graphic.png)\n", "\n", "#### 📋 Class Attributes\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ParameterType & DefaultDescription
llmBaseChatModel
default=None		A langchain llm `BaseChatModel`. User is responsible for specifying temperature and other relevant parameters to the constructor of their `llm` object.
scorersList[str]
default=None		 Specifies which white-box UQ scorers to include. Must be subset of [\"normalized_probability\", \"min_probability\", \"sequence_probability\", \"max_token_negentropy\", \"mean_token_negentropy\", \"probability_margin\", \"monte_carlo_negentropy\", \"consistency_and_confidence\", \"semantic_negentropy\", \"semantic_density\", \"p_true\"]. If None, defaults to [\"normalized_probability\", \"min_probability\"].
system_promptstr or None
default=\"You are a helpful assistant.\"		Optional argument for user to provide custom system prompt for the LLM.
max_calls_per_minint
default=None		Specifies how many API calls to make per minute to avoid rate limit errors. By default, no limit is specified.
sampling_temperaturefloat
default=1		The 'temperature' parameter for LLM to use when generating sampled LLM responses. Only applies to \"monte_carlo_negentropy\", \"consistency_and_confidence\", \"semantic_negentropy\", \"semantic_density\". Must be greater than 0.
\n", "\n", "#### 🔍 Parameter Groups\n", "\n", "
\n", "
\n", "

🧠 Model-Specific

\n", " \n", "
\n", "
\n", "

📊 Confidence Scores

\n", " \n", "
\n", "
\n", "

⚡ Performance

\n", " \n", "
\n", "
" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "tags": [] }, "outputs": [], "source": [ "wbuq = WhiteBoxUQ(\n", " llm=llm,\n", " scorers=[\n", " \"monte_carlo_probability\", # requires multiple sampled responses per prompt\n", " \"consistency_and_confidence\", # requires multiple sampled responses per prompt\n", " \"p_true\", # generates one additional response per prompt, acts as logprobs-based self-judge\n", " ],\n", " max_calls_per_min=125,\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 🔄 Class Methods\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
MethodDescription & Parameters
WhiteBoxUQ.generate_and_score\n", "

Generate LLM responses and compute confidence scores for the provided prompts.

\n", "

Parameters:

\n", "
    \n", "
  • prompts - (List[str] or List[List[BaseMessage]]) A list of input prompts for the model.
    • \n", "
  • num_responses - (int, default=5) The number of sampled responses to generate for sampling-based white-box UQ methods. Only applies to \"monte_carlo_negentropy\", \"consistency_and_confidence\", \"semantic_negentropy\", \"semantic_density\".
    • \n", "
  • show_progress_bars - (bool, default=True) If True, displays a progress bar while generating and scoring responses.
    • \n", "
\n", "

Returns: UQResult containing data (prompts, responses, log probabilities, and confidence scores) and metadata

\n", "
\n", " 💡 Best For: Complete end-to-end uncertainty quantification when starting with prompts.\n", "
\n", "
BlackBoxUQ.score\n", "

Compute confidence scores on provided LLM responses and logprobs. Should only be used if responses and sampled responses are already generated with logprobs.

\n", "

Parameters:

\n", "
    \n", "
  • responses - (List[str]) A list of LLM responses for the prompts.
    • \n", "
  • logprob_results - (List[List[str]]) A list of dictionaries, each returned by BaseChatModel.agenerate corresponding to responses.
    • \n", "
  • sampled_responses - (List[List[str]], default=None) A list of lists of sampled LLM responses for each prompt. Used to compute consistency scores by comparing to the corresponding response from responses. Required only for \"monte_carlo_negentropy\", \"consistency_and_confidence\", \"semantic_negentropy\", \"semantic_density\" scorers.
    • \n", "
  • sampled_logprob_results - (List[List[str]], default=None) List of list of dictionaries, each returned by BaseChatModel.agenerate. These must correspond to sampled_responses. Required only for \"monte_carlo_negentropy\", \"consistency_and_confidence\", \"semantic_negentropy\", \"semantic_density\" scorers.
    • \n", "
  • prompts - (List[List[str]], default=None) List of prompts from which responses were generated. Required only for \"p_true\" scorer.
    • \n", "
  • show_progress_bars - (bool, default=True) If True, displays a progress bar while scoring responses.
    • \n", "
\n", "

Returns: UQResult containing data (responses, sampled responses, and confidence scores) and metadata

\n", "
\n", " 💡 Best For: Computing uncertainty scores when responses and logprobs are already generated elsewhere.\n", "
\n", "
" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "tags": [] }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "ab71f72963e74b979bd369a1b508c123", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Output()" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
\n"
      ],
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "results = await wbuq.generate_and_score(prompts=prompts, num_responses=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
promptresponselogprobsampled_responsessampled_logprobconsistency_and_confidencemonte_carlo_probabilityp_true
0When you solve this math problem only return t...72[{'token': '72', 'bytes': [55, 50], 'logprob':...[72, 72, 72, 72, 72][[{'token': '72', 'bytes': [55, 50], 'logprob'...0.9998190.9999550.377549
1When you solve this math problem only return t...$10[{'token': '$', 'bytes': [36], 'logprob': -0.0...[$10, $10, $10, $10, $10][[{'token': '$', 'bytes': [36], 'logprob': -0....0.9944630.9944150.047430
2When you solve this math problem only return t...$20[{'token': '$', 'bytes': [36], 'logprob': -0.0...[$20, $20, $20, $20, $10][[{'token': '$', 'bytes': [36], 'logprob': -0....0.9230750.8903580.777260
3When you solve this math problem only return t...48[{'token': '48', 'bytes': [52, 56], 'logprob':...[48, 48, 48, 48, 48][[{'token': '48', 'bytes': [52, 56], 'logprob'...0.9947550.9961960.182436
4When you solve this math problem only return t...624[{'token': '624', 'bytes': [54, 50, 52], 'logp...[624, 624 pages., 624, 624, 624][[{'token': '624', 'bytes': [54, 50, 52], 'log...0.9548160.9233050.981987
\n",
       "
"
      ],
      "text/plain": [
       "                                              prompt response  \\\n",
       "0  When you solve this math problem only return t...       72   \n",
       "1  When you solve this math problem only return t...      $10   \n",
       "2  When you solve this math problem only return t...      $20   \n",
       "3  When you solve this math problem only return t...       48   \n",
       "4  When you solve this math problem only return t...      624   \n",
       "\n",
       "                                             logprob  \\\n",
       "0  [{'token': '72', 'bytes': [55, 50], 'logprob':...   \n",
       "1  [{'token': '$', 'bytes': [36], 'logprob': -0.0...   \n",
       "2  [{'token': '$', 'bytes': [36], 'logprob': -0.0...   \n",
       "3  [{'token': '48', 'bytes': [52, 56], 'logprob':...   \n",
       "4  [{'token': '624', 'bytes': [54, 50, 52], 'logp...   \n",
       "\n",
       "                  sampled_responses  \\\n",
       "0              [72, 72, 72, 72, 72]   \n",
       "1         [$10, $10, $10, $10, $10]   \n",
       "2         [$20, $20, $20, $20, $10]   \n",
       "3              [48, 48, 48, 48, 48]   \n",
       "4  [624, 624 pages., 624, 624, 624]   \n",
       "\n",
       "                                     sampled_logprob  \\\n",
       "0  [[{'token': '72', 'bytes': [55, 50], 'logprob'...   \n",
       "1  [[{'token': '$', 'bytes': [36], 'logprob': -0....   \n",
       "2  [[{'token': '$', 'bytes': [36], 'logprob': -0....   \n",
       "3  [[{'token': '48', 'bytes': [52, 56], 'logprob'...   \n",
       "4  [[{'token': '624', 'bytes': [54, 50, 52], 'log...   \n",
       "\n",
       "   consistency_and_confidence  monte_carlo_probability    p_true  \n",
       "0                    0.999819                 0.999955  0.377549  \n",
       "1                    0.994463                 0.994415  0.047430  \n",
       "2                    0.923075                 0.890358  0.777260  \n",
       "3                    0.994755                 0.996196  0.182436  \n",
       "4                    0.954816                 0.923305  0.981987  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_df = results.to_df()\n",
    "result_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "## 3. Evaluate Hallucination Detection Performance"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To evaluate hallucination detection performance, we 'grade' the responses against an answer key. Note the `math_postprocessor` is specific to our use case (math questions). **If you are using your own prompts/questions, update the grading method accordingly**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "
\n",
       "\n",
       "\n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "  \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "    \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "      \n",
       "    \n",
       "  \n",
       "
promptresponselogprobsampled_responsessampled_logprobconsistency_and_confidencemonte_carlo_probabilityp_trueanswerresponse_correct
0When you solve this math problem only return t...72[{'token': '72', 'bytes': [55, 50], 'logprob':...[72, 72, 72, 72, 72][[{'token': '72', 'bytes': [55, 50], 'logprob'...0.9998190.9999550.37754972True
1When you solve this math problem only return t...$10[{'token': '$', 'bytes': [36], 'logprob': -0.0...[$10, $10, $10, $10, $10][[{'token': '$', 'bytes': [36], 'logprob': -0....0.9944630.9944150.04743010True
2When you solve this math problem only return t...$20[{'token': '$', 'bytes': [36], 'logprob': -0.0...[$20, $20, $20, $20, $10][[{'token': '$', 'bytes': [36], 'logprob': -0....0.9230750.8903580.7772605False
3When you solve this math problem only return t...48[{'token': '48', 'bytes': [52, 56], 'logprob':...[48, 48, 48, 48, 48][[{'token': '48', 'bytes': [52, 56], 'logprob'...0.9947550.9961960.18243642False
4When you solve this math problem only return t...624[{'token': '624', 'bytes': [54, 50, 52], 'logp...[624, 624 pages., 624, 624, 624][[{'token': '624', 'bytes': [54, 50, 52], 'log...0.9548160.9233050.981987624True
\n",
       "
"
      ],
      "text/plain": [
       "                                              prompt response  \\\n",
       "0  When you solve this math problem only return t...       72   \n",
       "1  When you solve this math problem only return t...      $10   \n",
       "2  When you solve this math problem only return t...      $20   \n",
       "3  When you solve this math problem only return t...       48   \n",
       "4  When you solve this math problem only return t...      624   \n",
       "\n",
       "                                             logprob  \\\n",
       "0  [{'token': '72', 'bytes': [55, 50], 'logprob':...   \n",
       "1  [{'token': '$', 'bytes': [36], 'logprob': -0.0...   \n",
       "2  [{'token': '$', 'bytes': [36], 'logprob': -0.0...   \n",
       "3  [{'token': '48', 'bytes': [52, 56], 'logprob':...   \n",
       "4  [{'token': '624', 'bytes': [54, 50, 52], 'logp...   \n",
       "\n",
       "                  sampled_responses  \\\n",
       "0              [72, 72, 72, 72, 72]   \n",
       "1         [$10, $10, $10, $10, $10]   \n",
       "2         [$20, $20, $20, $20, $10]   \n",
       "3              [48, 48, 48, 48, 48]   \n",
       "4  [624, 624 pages., 624, 624, 624]   \n",
       "\n",
       "                                     sampled_logprob  \\\n",
       "0  [[{'token': '72', 'bytes': [55, 50], 'logprob'...   \n",
       "1  [[{'token': '$', 'bytes': [36], 'logprob': -0....   \n",
       "2  [[{'token': '$', 'bytes': [36], 'logprob': -0....   \n",
       "3  [[{'token': '48', 'bytes': [52, 56], 'logprob'...   \n",
       "4  [[{'token': '624', 'bytes': [54, 50, 52], 'log...   \n",
       "\n",
       "   consistency_and_confidence  monte_carlo_probability    p_true answer  \\\n",
       "0                    0.999819                 0.999955  0.377549     72   \n",
       "1                    0.994463                 0.994415  0.047430     10   \n",
       "2                    0.923075                 0.890358  0.777260      5   \n",
       "3                    0.994755                 0.996196  0.182436     42   \n",
       "4                    0.954816                 0.923305  0.981987    624   \n",
       "\n",
       "   response_correct  \n",
       "0              True  \n",
       "1              True  \n",
       "2             False  \n",
       "3             False  \n",
       "4              True  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Populate correct answers\n",
    "result_df[\"answer\"] = gsm8k.answer\n",
    "\n",
    "# Grade responses against correct answers\n",
    "result_df[\"response_correct\"] = [math_postprocessor(r) == a for r, a in zip(result_df[\"response\"], gsm8k[\"answer\"])]\n",
    "result_df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Baseline LLM accuracy: 0.53\n"
     ]
    }
   ],
   "source": [
    "print(f\"\"\"Baseline LLM accuracy: {np.mean(result_df[\"response_correct\"])}\"\"\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 3.1 Filtered LLM Accuracy Evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here, we explore ‘filtered accuracy’ as a metric for evaluating the performance of our confidence scores. Filtered accuracy measures the change in LLM performance when responses with confidence scores below a specified threshold are excluded. By adjusting the confidence score threshold, we can observe how the accuracy of the LLM improves as less certain responses are filtered out.\n",
    "\n",
    "We will plot the filtered accuracy across various confidence score thresholds to visualize the relationship between confidence and LLM accuracy. This analysis helps in understanding the trade-off between response coverage (measured by sample size below) and LLM accuracy, providing insights into the reliability of the LLM’s outputs. We conduct this analysis separately for each of our scorers. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "
"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for scorer in [\"monte_carlo_probability\", \"consistency_and_confidence\", \"p_true\"]:\n",
    "    plot_model_accuracies(scores=result_df[scorer], correct_indicators=result_df.response_correct, title=f\"LLM Accuracy by {scorer} Score Threshold\", display_percentage=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 3.2 Precision, Recall, F1-Score of Hallucination Detection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lastly, we compute the optimal threshold for binarizing confidence scores, using F1-score as the objective. Using this threshold, we compute precision, recall, and F1-score for black box scorer predictions of whether responses are correct."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "========================================================================================================================\n",
      "Metrics                       monte_carlo_probability       consistency_and_confidence    p_true                        \n",
      "------------------------------------------------------------------------------------------------------------------------\n",
      "Precision                     0.885                         0.909                         0.522                         \n",
      "Recall                        0.885                         0.769                         0.923                         \n",
      "F1-score                      0.885                         0.833                         0.667                         \n",
      "------------------------------------------------------------------------------------------------------------------------\n",
      "F-1 optimal threshold         0.64                          0.74                          0.02                          \n",
      "========================================================================================================================\n"
     ]
    }
   ],
   "source": [
    "# instantiate UQLM tuner object for threshold selection\n",
    "split = len(result_df) // 2\n",
    "t = Tuner()\n",
    "\n",
    "correct_indicators = (result_df.response_correct) * 1  # Whether responses is actually correct\n",
    "metric_values = {\"Precision\": [], \"Recall\": [], \"F1-score\": []}\n",
    "optimal_thresholds = []\n",
    "for confidence_score in wbuq.scorers:\n",
    "    # tune threshold on first half\n",
    "    y_scores = result_df[confidence_score]\n",
    "    y_scores_tune = y_scores[0:split]\n",
    "    y_true_tune = correct_indicators[0:split]\n",
    "    best_threshold = t.tune_threshold(y_scores=y_scores_tune, correct_indicators=y_true_tune, thresh_objective=\"fbeta_score\")\n",
    "\n",
    "    y_pred = [(s > best_threshold) * 1 for s in y_scores]  # predicts whether response is correct based on confidence score\n",
    "    optimal_thresholds.append(best_threshold)\n",
    "\n",
    "    # evaluate on last half\n",
    "    y_true_eval = correct_indicators[split:]\n",
    "    y_pred_eval = y_pred[split:]\n",
    "    metric_values[\"Precision\"].append(precision_score(y_true=y_true_eval, y_pred=y_pred_eval))\n",
    "    metric_values[\"Recall\"].append(recall_score(y_true=y_true_eval, y_pred=y_pred_eval))\n",
    "    metric_values[\"F1-score\"].append(f1_score(y_true=y_true_eval, y_pred=y_pred_eval))\n",
    "\n",
    "# print results\n",
    "header = f\"{'Metrics':<30}\" + \"\".join([f\"{scorer_name:<30}\" for scorer_name in wbuq.scorers])\n",
    "print(\"=\" * len(header) + \"\\n\" + header + \"\\n\" + \"-\" * len(header))\n",
    "for metric in metric_values.keys():\n",
    "    print(f\"{metric:<30}\" + \"\".join([f\"{round(x_, 3):<30}\" for x_ in metric_values[metric]]))\n",
    "print(\"-\" * len(header))\n",
    "print(f\"{'F-1 optimal threshold':<30}\" + \"\".join([f\"{round(x_, 3):<30}\" for x_ in optimal_thresholds]))\n",
    "print(\"=\" * len(header))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "## 4. Scorer Definitions\n",
    "White-box UQ scorers leverage token probabilities of the LLM's generated response to quantify uncertainty. All scorers have outputs ranging from 0 to 1, with higher values indicating higher confidence. We define several multi-generation white-box UQ scorers below. \n",
    "\n",
    "Let the tokenization LLM response $y_i$ be denoted as $\\{t_1,...,t_{L_i}\\}$, where $L_i$ denotes the number of tokens the response. Further, let $y_1,...,y_m$ denote $m$ sampled responses generated from the same prompt.\n",
    "\n",
    "### Monte Carlo Sequence Probability (`monte_carlo_probability`)\n",
    "Monte Carlo Sequence Probability (MCSP) computes the average length-normalized sequence probability across sampled responses. \n",
    "\n",
    "\n",
    "\n",
    "$$        MCSP(y_1,y_2,...,y_m) =  \\frac{1}{m} \\sum_{i=1}^m  \\prod_{t \\in y_i}  p_t^{\\frac{1}{L_i}}   $$    \n",
    "\n",
    "\n",
    "For more on this scorer, refer to [Kuhn et al., 2023](https://arxiv.org/abs/2302.09664). \n",
    "\n",
    "\n",
    "### Consistency and Confidence Approach (CoCoA) (`consistency_and_confidence`)\n",
    "Consistency and Confidence Approach (CoCoA) leverages two distinct signals: 1) similarity between an original response $y_0$ and a set of sampled responses $y_1,...,y_m$ and token probabilities from the original response $y_0$. \n",
    "\n",
    "We first get the length-normalized token probability of our original response:\n",
    "\n",
    "$$        LNTP(y_0) = \\prod_{t \\in y_0}  p_t^{\\frac{1}{L_0}}.$$    \n",
    "\n",
    "\n",
    "We then obtain average cosine similarity across pairings of the original response with all sampled responses, normalized to a [0,1] scale:\n",
    "\n",
    "\n",
    " $$       NCS(y_0; y_1,...,y_m) = \\frac{1}{m} \\sum_{i=1}^m \\frac{\\cos(y_0; y_i) + 1}{2}.$$    \n",
    "\n",
    "\n",
    "CoCoa is then calculated as the product of these two terms.\n",
    "\n",
    "\n",
    " $$       CoCoA(y_0; y_1,...,y_m) = LNTP(y_0) * NCS(y_0; y_1,...,y_m).$$    \n",
    "\n",
    "\n",
    "For more on this scorer, refer to [Vashurin et al., 2025](https://arxiv.org/abs/2502.04964).\n",
    "\n",
    "### Normalized Semantic Negentropy\n",
    "Normalized Semantic Negentropy (NSN) normalizes the standard computation of discrete semantic entropy to be increasing with higher confidence and have [0,1] support. Under this approach, responses are clustered using an NLI model based on mutual entailment. After obtaining the set of clusters $\\mathcal{C}$, semantic entropy is computed as:\n",
    "\n",
    "\n",
    "$$        SE(y_i; \\tilde{\\mathbf{y}}_i) = - \\sum_{C \\in \\mathcal{C}} P(C|y_i, \\tilde{\\mathbf{y}}_i)\\log P(C|y_i, \\tilde{\\mathbf{y}}_i),$$    \n",
    "\n",
    "\n",
    "where $P(C|y_i, \\tilde{\\mathbf{y}}_i)$ is calculated as the average across response-level sequence probabilities (normalized or otherwise), and $\\mathcal{C}$ denotes the full set of clusters of $\\{y_i\\} \\cup \\tilde{\\mathbf{y}}_i$.\n",
    "\n",
    "To ensure that we have a normalized confidence score with $[0,1]$ support and with higher values corresponding to higher confidence, we implement the following normalization to arrive at *ormalized Semantic Negentropy* (NSN):\n",
    "\n",
    "$$        NSN(y_i; \\tilde{\\mathbf{y}}_i) = 1 - \\frac{SE(y_i; \\tilde{\\mathbf{y}}_i)}{\\log m},$$    \n",
    "\n",
    "where $\\log m$ is included to normalize the support. For more on semantic entropy, refer to [Farquhar et al., 2024](https://www.nature.com/articles/s41586-024-07421-0); [Kuhn et al., 2023](https://arxiv.org/pdf/2302.09664), and for more on our normalized version, refer to [Bouchard & Chauhan, 2025](https://arxiv.org/abs/2504.19254).\n",
    "\n",
    "### Semantic Density\n",
    "Semantic Density (SD) approximates a probability density function (PDF) in semantic space for estimating response correctness. Given a prompt $x$ with candidate response $y_*$, the objective is to construct a PDF that assigns higher density to regions in the semantic space that correspond to correct responses. We begin by sampling $M$ unique reference responses $y_i$ (for $i = 1, 2, \\dots, M$) conditioned on $x$. For any pair of responses $y_i, y_j$ with corresponding embeddings $v_i, v_j$, the semantic distance is estimated as\n",
    "\n",
    "\n",
    "$$        \\mathbb{E}(\\Vert v_i,v_j \\Vert^2) = p_c(y_i, y_j | x) + \\dfrac{1}{2} \\cdot p_n(y_i, y_j | x)$$    \n",
    "\n",
    "\n",
    "where $p_c, p_n$ denote the contradiction and neutrality scores returned by a natural language inference (NLI) model, respectively. This estimated distance is incorporated in the kernel function $K$ to smooth out the reference responses into a continuous distribution. The kernel function value can be obtained as\n",
    "\n",
    "\n",
    " $$       K(v_*, v_i) = (1 - \\mathbb{E}(\\Vert v_* - v_i \\Vert^2))\\mathbf{1}_{\\mathbb{E}(\\Vert v_* - v_i \\Vert) \\leq 1}$$    \n",
    "\n",
    "\n",
    "where $\\bf{1}$ is the indicator function such that $\\bf{1}_{\\text{condition}} = 1$ when the condition holds and $0$ otherwise. The final semantic density score is computed as\n",
    "\n",
    "\n",
    " $$       SD(y_* | x) = \\dfrac{1}{\\sum^M_{i=1}\\sqrt[L_i]{p(y_i|x)}}\\sum^M_{i=1}\\sqrt[L_i]{p(y_i|x)}K(v_* - v_i)$$    \n",
    "\n",
    "\n",
    "where $L_i$ denotes the length of $y_i$.\n",
    "\n",
    "### P(True) (`p_true`)\n",
    "\n",
    "The P(True) presents an LLM with a concatenation of a question and its own previous response. The LLM is asked to classify this statement as \"True\" or \"False.\" We derive this confidence score directly from the model's token probability for answering \"True\" (or equivalently, 1-P(\"False\") if the model answers \"False\"). For more on this scorer, refer to [Kadavath et al., 2022](https://arxiv.org/abs/2207.05221)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "© 2025 CVS Health and/or one of its affiliates. All rights reserved."
   ]
  }
 ],
 "metadata": {
  "environment": {
   "kernel": "uqlm_my_test",
   "name": "workbench-notebooks.m126",
   "type": "gcloud",
   "uri": "us-docker.pkg.dev/deeplearning-platform-release/gcr.io/workbench-notebooks:m126"
  },
  "kernelspec": {
   "display_name": "uqlm_my_test",
   "language": "python",
   "name": "uqlm_my_test"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}